Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1776. Min Range: -8.1776
Max Act: 8.1776. Min Act: -0.1700
Data Index: 1616812 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1776. Min Range: -8.1776
Max Act: 8.1463. Min Act: -0.1700
Data Index: 8128504 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1776. Min Range: -8.1776
Max Act: 8.0838. Min Act: -0.1700
Data Index: 6113115 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1776. Min Range: -8.1776
Max Act: 8.0213. Min Act: -0.1700
Data Index: 8379484 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9901. Min Act: -0.1700
Data Index: 1749552 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1776. Min Range: -8.1776
Max Act: 8.0213. Min Act: -0.1700
Data Index: 77697 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1776. Min Range: -8.1776
Max Act: 8.0213. Min Act: -0.1700
Data Index: 2539089 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9901. Min Act: -0.1700
Data Index: 4588593 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9901. Min Act: -0.1700
Data Index: 7706336 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9901. Min Act: -0.1700
Data Index: 1250618 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9901. Min Act: -0.1700
Data Index: 4592948 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9588. Min Act: -0.1700
Data Index: 8600152 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9276. Min Act: -0.1700
Data Index: 3219001 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9276. Min Act: -0.1700
Data Index: 3062057 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9276. Min Act: -0.1700
Data Index: 3033458 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9276. Min Act: -0.1700
Data Index: 7659877 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9276. Min Act: -0.1700
Data Index: 5868217 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9276. Min Act: -0.1700
Data Index: 640947 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.8963. Min Act: -0.1700
Data Index: 4567032 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1776. Min Range: -8.1776
Max Act: 7.9276. Min Act: -0.1700
Data Index: 5230746 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19