Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3244 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.9885. Min Act: -0.1700
Data Index: 3313194 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.8321. Min Act: -0.1700
Data Index: 3313946 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.6757. Min Act: -0.1700
Data Index: 55728 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.6444. Min Act: -0.1700
Data Index: 5759823 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5505. Min Act: -0.1700
Data Index: 7162643 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5505. Min Act: -0.1700
Data Index: 1575905 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5505. Min Act: -0.1700
Data Index: 6592032 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5505. Min Act: -0.1700
Data Index: 5593089 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5192. Min Act: -0.1700
Data Index: 8789407 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5192. Min Act: -0.1700
Data Index: 1872006 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5192. Min Act: -0.1700
Data Index: 6901614 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5192. Min Act: -0.1700
Data Index: 5879421 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5192. Min Act: -0.1700
Data Index: 8830911 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.5192. Min Act: -0.1700
Data Index: 4648656 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.4879. Min Act: -0.1700
Data Index: 175730 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.4879. Min Act: -0.1700
Data Index: 4385961 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.4722. Min Act: -0.1700
Data Index: 6501648 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.4879. Min Act: -0.1700
Data Index: 4486804 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.4879. Min Act: -0.1700
Data Index: 1127102 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9885. Min Range: -3.9885
Max Act: 3.4879. Min Act: -0.1700
Data Index: 6257188 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19