Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0488. Min Range: -6.0488
Max Act: 6.0488. Min Act: -0.1700
Data Index: 546460 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.9551. Min Act: -0.1700
Data Index: 6816925 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.9551. Min Act: -0.1700
Data Index: 6818798 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8926. Min Act: -0.1700
Data Index: 3365788 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8926. Min Act: -0.1700
Data Index: 7390922 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8613. Min Act: -0.1700
Data Index: 8649193 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8613. Min Act: -0.1700
Data Index: 1581312 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8613. Min Act: -0.1700
Data Index: 3868947 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8613. Min Act: -0.1700
Data Index: 5443469 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8301. Min Act: -0.1700
Data Index: 733781 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8301. Min Act: -0.1700
Data Index: 4811010 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8301. Min Act: -0.1700
Data Index: 5930810 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.7988. Min Act: -0.1700
Data Index: 5307233 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.8301. Min Act: -0.1700
Data Index: 7899308 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.7988. Min Act: -0.1700
Data Index: 6148501 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.7988. Min Act: -0.1700
Data Index: 1079538 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.7988. Min Act: -0.1700
Data Index: 5000656 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.7988. Min Act: -0.1700
Data Index: 493026 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.7988. Min Act: -0.1700
Data Index: 6517766 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0488. Min Range: -6.0488
Max Act: 5.7676. Min Act: -0.1700
Data Index: 4881109 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19