Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 432 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.7379. Min Act: -0.1700
Data Index: 1243901 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.7379. Min Act: -0.1700
Data Index: 8381322 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.6129. Min Act: -0.1700
Data Index: 4498700 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.6129. Min Act: -0.1700
Data Index: 473371 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.5817. Min Act: -0.1700
Data Index: 6340639 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.5817. Min Act: -0.1700
Data Index: 2789275 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.5817. Min Act: -0.1700
Data Index: 3961026 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.5192. Min Act: -0.1700
Data Index: 8017416 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4879. Min Act: -0.1700
Data Index: 3459380 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4879. Min Act: -0.1700
Data Index: 2563706 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4567. Min Act: -0.1700
Data Index: 7059707 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4567. Min Act: -0.1700
Data Index: 3876502 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4254. Min Act: -0.1700
Data Index: 5467302 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4254. Min Act: -0.1700
Data Index: 3461430 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4567. Min Act: -0.1700
Data Index: 1369992 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4254. Min Act: -0.1700
Data Index: 4274402 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4254. Min Act: -0.1700
Data Index: 543244 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.4254. Min Act: -0.1700
Data Index: 5037913 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.3942. Min Act: -0.1700
Data Index: 8335564 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7379. Min Range: -4.7379
Max Act: 4.3942. Min Act: -0.1700
Data Index: 1987696 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19