Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2819 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.0948. Min Range: -14.0948
Max Act: 14.0948. Min Act: -0.1700
Data Index: 7433097 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.0948. Min Range: -14.0948
Max Act: 14.0323. Min Act: -0.1700
Data Index: 3837303 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.0948. Min Range: -14.0948
Max Act: 14.0323. Min Act: -0.1700
Data Index: 8473277 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.8448. Min Act: -0.1700
Data Index: 8429386 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.7823. Min Act: -0.1700
Data Index: 3278259 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.7198. Min Act: -0.1699
Data Index: 7373668 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.7198. Min Act: -0.1700
Data Index: 4705312 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.7198. Min Act: -0.1700
Data Index: 3752524 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.6573. Min Act: -0.1700
Data Index: 8336994 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.6573. Min Act: -0.1700
Data Index: 2666389 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.6573. Min Act: -0.1700
Data Index: 303192 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.6573. Min Act: -0.1700
Data Index: 377472 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.5948. Min Act: -0.1700
Data Index: 5931140 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.5323. Min Act: -0.1699
Data Index: 5481531 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.5323. Min Act: -0.1700
Data Index: 7086674 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.5323. Min Act: -0.1700
Data Index: 8377762 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.5323. Min Act: -0.1700
Data Index: 370647 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.4698. Min Act: -0.1700
Data Index: 7749485 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.5323. Min Act: -0.1700
Data Index: 2011399 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.0948. Min Range: -14.0948
Max Act: 13.4698. Min Act: -0.1700
Data Index: 5020436 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19