Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7667. Min Range: -12.7667
Max Act: 12.7667. Min Act: -0.1700
Data Index: 7706010 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7667. Min Range: -12.7667
Max Act: 12.3917. Min Act: -0.1700
Data Index: 4012583 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7667. Min Range: -12.7667
Max Act: 12.3292. Min Act: -0.1700
Data Index: 6446582 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7667. Min Range: -12.7667
Max Act: 12.2667. Min Act: -0.1700
Data Index: 4803265 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7667. Min Range: -12.7667
Max Act: 12.1417. Min Act: -0.1700
Data Index: 7236305 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7667. Min Range: -12.7667
Max Act: 12.1417. Min Act: -0.1700
Data Index: 1307537 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7667. Min Range: -12.7667
Max Act: 12.0792. Min Act: -0.1700
Data Index: 7891312 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7667. Min Range: -12.7667
Max Act: 12.0792. Min Act: -0.1700
Data Index: 8437447 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7667. Min Range: -12.7667
Max Act: 12.0167. Min Act: -0.1700
Data Index: 7649030 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.8292. Min Act: -0.1700
Data Index: 2558077 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.8292. Min Act: -0.1700
Data Index: 4449049 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.7667. Min Act: -0.1700
Data Index: 5571837 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.8292. Min Act: -0.1700
Data Index: 8682209 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.7667. Min Act: -0.1700
Data Index: 3724684 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.7667. Min Act: -0.1700
Data Index: 4347656 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.6417. Min Act: -0.1700
Data Index: 3689966 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.7667. Min Act: -0.1700
Data Index: 3528715 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.7042. Min Act: -0.1700
Data Index: 6965070 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.7042. Min Act: -0.1700
Data Index: 1101903 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7667. Min Range: -12.7667
Max Act: 11.6417. Min Act: -0.1700
Data Index: 5321089 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19