Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.7978. Min Act: -0.1700
Data Index: 2558496 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.6727. Min Act: -0.1700
Data Index: 706907 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.6414. Min Act: -0.1700
Data Index: 4174016 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.6414. Min Act: -0.1700
Data Index: 8496452 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.6101. Min Act: -0.1700
Data Index: 706908 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.5162. Min Act: -0.1700
Data Index: 2771164 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.5162. Min Act: -0.1699
Data Index: 5412365 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.5162. Min Act: -0.1700
Data Index: 4544224 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.5162. Min Act: -0.1700
Data Index: 7979544 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4849. Min Act: -0.1700
Data Index: 2101868 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.5162. Min Act: -0.1700
Data Index: 3738309 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4849. Min Act: -0.1700
Data Index: 8609554 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4849. Min Act: -0.1700
Data Index: 3236270 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4849. Min Act: -0.1700
Data Index: 2447347 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4849. Min Act: -0.1700
Data Index: 335230 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4849. Min Act: -0.1700
Data Index: 5412370 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4535. Min Act: -0.1700
Data Index: 3476688 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4535. Min Act: -0.1700
Data Index: 7596788 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4535. Min Act: -0.1700
Data Index: 122454 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7978. Min Range: -3.7978
Max Act: 3.4222. Min Act: -0.1700
Data Index: 3454453 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19