Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.5323. Min Act: -0.1700
Data Index: 3617962 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.4187. Min Act: -0.1700
Data Index: 2343733 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.3697. Min Act: -0.1700
Data Index: 1151382 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.3533. Min Act: -0.1700
Data Index: 3950049 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.3533. Min Act: -0.1700
Data Index: 177423 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.3205. Min Act: -0.1700
Data Index: 4789336 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.3041. Min Act: -0.1700
Data Index: 6099029 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.3041. Min Act: -0.1700
Data Index: 4104903 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2876. Min Act: -0.1700
Data Index: 7607585 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2712. Min Act: -0.1700
Data Index: 8403564 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2712. Min Act: -0.1700
Data Index: 4968553 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2712. Min Act: -0.1700
Data Index: 5523852 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2712. Min Act: -0.1700
Data Index: 8136290 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2547. Min Act: -0.1700
Data Index: 1838080 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2876. Min Act: -0.1700
Data Index: 4760858 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2547. Min Act: -0.1700
Data Index: 3602922 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2547. Min Act: -0.1700
Data Index: 4628013 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2381. Min Act: -0.1700
Data Index: 8063575 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2547. Min Act: -0.1700
Data Index: 6683511 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2547. Min Act: -0.1700
Data Index: 8368730 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19