Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5278 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6812. Min Act: -0.1700
Data Index: 4405605 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5716. Min Act: -0.1700
Data Index: 5894732 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5560. Min Act: -0.1700
Data Index: 4609102 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5403. Min Act: -0.1700
Data Index: 6141781 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5246. Min Act: -0.1700
Data Index: 748092 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5090. Min Act: -0.1700
Data Index: 7217761 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5090. Min Act: -0.1700
Data Index: 8629901 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4933. Min Act: -0.1700
Data Index: 577950 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4776. Min Act: -0.1700
Data Index: 3722500 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4933. Min Act: -0.1700
Data Index: 8367381 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4776. Min Act: -0.1700
Data Index: 5975415 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4776. Min Act: -0.1700
Data Index: 987015 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4776. Min Act: -0.1700
Data Index: 340426 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4776. Min Act: -0.1700
Data Index: 3510922 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4463. Min Act: -0.1700
Data Index: 4734010 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4463. Min Act: -0.1700
Data Index: 7310271 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4306. Min Act: -0.1700
Data Index: 4775834 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4306. Min Act: -0.1700
Data Index: 1793754 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4306. Min Act: -0.1700
Data Index: 6648443 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4306. Min Act: -0.1700
Data Index: 1551539 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19