Understanding Addition in Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Quirke, Philip, Barez, Fazl
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913326804500480
author Quirke, Philip
Barez, Fazl
author_facet Quirke, Philip
Barez, Fazl
contents Understanding the inner workings of machine learning models like Transformers is vital for their safe and ethical use. This paper provides a comprehensive analysis of a one-layer Transformer model trained to perform n-digit integer addition. Our findings suggest that the model dissects the task into parallel streams dedicated to individual digits, employing varied algorithms tailored to different positions within the digits. Furthermore, we identify a rare scenario characterized by high loss, which we explain. By thoroughly elucidating the model's algorithm, we provide new insights into its functioning. These findings are validated through rigorous testing and mathematical modeling, thereby contributing to the broader fields of model understanding and interpretability. Our approach opens the door for analyzing more complex tasks and multi-layer Transformer models.
format Preprint
id arxiv_https___arxiv_org_abs_2310_13121
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Understanding Addition in Transformers
Quirke, Philip
Barez, Fazl
Machine Learning
Artificial Intelligence
Understanding the inner workings of machine learning models like Transformers is vital for their safe and ethical use. This paper provides a comprehensive analysis of a one-layer Transformer model trained to perform n-digit integer addition. Our findings suggest that the model dissects the task into parallel streams dedicated to individual digits, employing varied algorithms tailored to different positions within the digits. Furthermore, we identify a rare scenario characterized by high loss, which we explain. By thoroughly elucidating the model's algorithm, we provide new insights into its functioning. These findings are validated through rigorous testing and mathematical modeling, thereby contributing to the broader fields of model understanding and interpretability. Our approach opens the door for analyzing more complex tasks and multi-layer Transformer models.
title Understanding Addition in Transformers
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2310.13121