Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1042. Min Range: -8.1042
Max Act: 8.1042. Min Act: -0.1700
Data Index: 6236975 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.9792. Min Act: -0.1700
Data Index: 3872560 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1042. Min Range: -8.1042
Max Act: 8.0105. Min Act: -0.1700
Data Index: 7909345 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.8542. Min Act: -0.1700
Data Index: 5290272 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.8230. Min Act: -0.1700
Data Index: 6612856 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.7605. Min Act: -0.1700
Data Index: 2592834 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.7605. Min Act: -0.1700
Data Index: 3526491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.7292. Min Act: -0.1700
Data Index: 3772201 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.6980. Min Act: -0.1700
Data Index: 8720907 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.6980. Min Act: -0.1700
Data Index: 3593646 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.7292. Min Act: -0.1700
Data Index: 692605 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.6667. Min Act: -0.1700
Data Index: 2418075 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.6355. Min Act: -0.1700
Data Index: 1674398 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.6042. Min Act: -0.1700
Data Index: 2162502 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.5730. Min Act: -0.1700
Data Index: 4967147 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.5417. Min Act: -0.1700
Data Index: 493677 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.5417. Min Act: -0.1700
Data Index: 7735367 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.4792. Min Act: -0.1700
Data Index: 8407641 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.4480. Min Act: -0.1700
Data Index: 3321651 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1042. Min Range: -8.1042
Max Act: 7.4480. Min Act: -0.1700
Data Index: 8771070 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19