Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 273 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.7941. Min Act: -0.1700
Data Index: 974903 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.7941. Min Act: -0.1700
Data Index: 5661344 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.7629. Min Act: -0.1700
Data Index: 5430822 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.5129. Min Act: -0.1700
Data Index: 7967232 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.5441. Min Act: -0.1700
Data Index: 5664695 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.5129. Min Act: -0.1700
Data Index: 809543 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.4816. Min Act: -0.1700
Data Index: 2819796 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.4816. Min Act: -0.1700
Data Index: 8367476 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.4504. Min Act: -0.1700
Data Index: 6690992 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.4504. Min Act: -0.1700
Data Index: 3770577 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.4191. Min Act: -0.1700
Data Index: 4188273 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.4191. Min Act: -0.1700
Data Index: 1000411 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.3879. Min Act: -0.1700
Data Index: 3111911 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.3879. Min Act: -0.1700
Data Index: 6036297 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.3566. Min Act: -0.1700
Data Index: 6925002 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.3566. Min Act: -0.1700
Data Index: 4804192 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.3566. Min Act: -0.1700
Data Index: 8093856 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.3879. Min Act: -0.1700
Data Index: 4148403 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.3566. Min Act: -0.1700
Data Index: 8706966 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7941. Min Range: -5.7941
Max Act: 5.3566. Min Act: -0.1700
Data Index: 8831692 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19