Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4867 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2188. Min Range: -7.2188
Max Act: 7.2188. Min Act: -0.1700
Data Index: 5221584 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.8126. Min Act: -0.1700
Data Index: 4043456 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7188. Min Act: -0.1700
Data Index: 4327739 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7188. Min Act: -0.1700
Data Index: 3429613 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.7188. Min Act: -0.1700
Data Index: 920972 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.6563. Min Act: -0.1700
Data Index: 4224940 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.6251. Min Act: -0.1700
Data Index: 5356071 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.5626. Min Act: -0.1700
Data Index: 362002 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.5626. Min Act: -0.1700
Data Index: 8614575 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.5626. Min Act: -0.1700
Data Index: 1097020 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.5626. Min Act: -0.1700
Data Index: 6906353 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.5313. Min Act: -0.1700
Data Index: 2612079 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.4688. Min Act: -0.1700
Data Index: 5592568 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.4688. Min Act: -0.1700
Data Index: 6362670 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.4376. Min Act: -0.1700
Data Index: 8485772 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.4376. Min Act: -0.1700
Data Index: 2061629 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.4376. Min Act: -0.1700
Data Index: 4700903 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.3438. Min Act: -0.1700
Data Index: 8516017 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.3751. Min Act: -0.1700
Data Index: 484541 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2188. Min Range: -7.2188
Max Act: 6.3438. Min Act: -0.1700
Data Index: 4111955 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19