Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.9698. Min Act: -0.1700
Data Index: 6062178 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.8135. Min Act: -0.1700
Data Index: 1996305 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.7823. Min Act: -0.1700
Data Index: 6766872 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.6260. Min Act: -0.1700
Data Index: 3120440 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.6260. Min Act: -0.1700
Data Index: 1776178 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.6260. Min Act: -0.1700
Data Index: 512816 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.6260. Min Act: -0.1700
Data Index: 1219663 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.5948. Min Act: -0.1700
Data Index: 3823749 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.5323. Min Act: -0.1700
Data Index: 554588 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.5010. Min Act: -0.1700
Data Index: 2435753 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.5010. Min Act: -0.1700
Data Index: 1568541 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.4698. Min Act: -0.1700
Data Index: 786301 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.4698. Min Act: -0.1700
Data Index: 2125698 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.4385. Min Act: -0.1700
Data Index: 4067160 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.4385. Min Act: -0.1700
Data Index: 6733991 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.4073. Min Act: -0.1700
Data Index: 8749260 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.4073. Min Act: -0.1700
Data Index: 1974962 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.4073. Min Act: -0.1700
Data Index: 4722765 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.2823. Min Act: -0.1700
Data Index: 4773059 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9698. Min Range: -7.9698
Max Act: 7.2510. Min Act: -0.1700
Data Index: 3838818 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19