Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3419 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.6518. Min Act: -0.1700
Data Index: 5136263 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.6518. Min Act: -0.1700
Data Index: 5937090 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.5893. Min Act: -0.1700
Data Index: 7399193 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.5268. Min Act: -0.1700
Data Index: 7890340 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.5268. Min Act: -0.1700
Data Index: 8033396 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.4018. Min Act: -0.1700
Data Index: 8202577 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.4018. Min Act: -0.1700
Data Index: 1687678 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.4018. Min Act: -0.1700
Data Index: 5055352 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.4018. Min Act: -0.1700
Data Index: 4381001 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.3393. Min Act: -0.1700
Data Index: 7066787 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.3393. Min Act: -0.1700
Data Index: 5956128 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.3393. Min Act: -0.1700
Data Index: 1820555 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.2768. Min Act: -0.1700
Data Index: 1313572 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.2768. Min Act: -0.1700
Data Index: 2373727 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.2143. Min Act: -0.1700
Data Index: 3612299 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.2143. Min Act: -0.1700
Data Index: 2921704 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.2768. Min Act: -0.1700
Data Index: 172930 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.2143. Min Act: -0.1700
Data Index: 1288470 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.2143. Min Act: -0.1700
Data Index: 3523637 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6518. Min Range: -8.6518
Max Act: 8.2143. Min Act: -0.1700
Data Index: 500207 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19