Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 638 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6777. Min Range: -8.6777
Max Act: 8.6777. Min Act: -0.1700
Data Index: 1251973 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6777. Min Range: -8.6777
Max Act: 8.1152. Min Act: -0.1700
Data Index: 2388445 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.8652. Min Act: -0.1700
Data Index: 1496242 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.7402. Min Act: -0.1700
Data Index: 8263927 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.7090. Min Act: -0.1700
Data Index: 4619346 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.6465. Min Act: -0.1700
Data Index: 1062650 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.6152. Min Act: -0.1700
Data Index: 7256534 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.6152. Min Act: -0.1700
Data Index: 1646280 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.5527. Min Act: -0.1700
Data Index: 3441948 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.5215. Min Act: -0.1700
Data Index: 360163 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.5215. Min Act: -0.1700
Data Index: 6514565 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.4590. Min Act: -0.1700
Data Index: 719084 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.4277. Min Act: -0.1700
Data Index: 2845407 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.3965. Min Act: -0.1700
Data Index: 8224815 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.3652. Min Act: -0.1700
Data Index: 3585187 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.3652. Min Act: -0.1700
Data Index: 2435087 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.3652. Min Act: -0.1700
Data Index: 2780090 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.3340. Min Act: -0.1700
Data Index: 748033 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.3340. Min Act: -0.1700
Data Index: 2358370 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6777. Min Range: -8.6777
Max Act: 7.3340. Min Act: -0.1700
Data Index: 4286425 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19