Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.9393. Min Act: -0.1700
Data Index: 2949589 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.9080. Min Act: -0.1700
Data Index: 3437515 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.9393. Min Act: -0.1700
Data Index: 4618767 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.9080. Min Act: -0.1700
Data Index: 6239667 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.8143. Min Act: -0.1700
Data Index: 5020266 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.8455. Min Act: -0.1700
Data Index: 832287 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.8455. Min Act: -0.1700
Data Index: 7390603 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.7830. Min Act: -0.1700
Data Index: 897364 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.7830. Min Act: -0.1700
Data Index: 735164 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.8143. Min Act: -0.1700
Data Index: 7928367 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.7518. Min Act: -0.1700
Data Index: 6710957 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.7518. Min Act: -0.1700
Data Index: 387207 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.6893. Min Act: -0.1700
Data Index: 7171198 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.6893. Min Act: -0.1700
Data Index: 5597901 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.6893. Min Act: -0.1700
Data Index: 7069369 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.6580. Min Act: -0.1700
Data Index: 1848716 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.5955. Min Act: -0.1700
Data Index: 8195846 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.5955. Min Act: -0.1700
Data Index: 2037359 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.5955. Min Act: -0.1700
Data Index: 2416926 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9393. Min Range: -6.9393
Max Act: 6.5955. Min Act: -0.1700
Data Index: 4320721 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19