Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4313. Min Range: -7.4313
Max Act: 7.4313. Min Act: -0.1700
Data Index: 1453302 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4313. Min Range: -7.4313
Max Act: 7.3063. Min Act: -0.1700
Data Index: 188280 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4313. Min Range: -7.4313
Max Act: 7.1813. Min Act: -0.1700
Data Index: 5012031 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9938. Min Act: -0.1700
Data Index: 7647701 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4313. Min Range: -7.4313
Max Act: 7.0251. Min Act: -0.1700
Data Index: 296888 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9938. Min Act: -0.1700
Data Index: 2919770 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4313. Min Range: -7.4313
Max Act: 7.0251. Min Act: -0.1700
Data Index: 3427478 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9938. Min Act: -0.1700
Data Index: 6342485 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9938. Min Act: -0.1700
Data Index: 7429868 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9626. Min Act: -0.1700
Data Index: 5273434 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9313. Min Act: -0.1697
Data Index: 8803356 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9313. Min Act: -0.1700
Data Index: 5043734 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9313. Min Act: -0.1700
Data Index: 5256257 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9313. Min Act: -0.1698
Data Index: 3935509 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.9001. Min Act: -0.1700
Data Index: 452711 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.8688. Min Act: -0.1700
Data Index: 5606660 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.8688. Min Act: -0.1700
Data Index: 6781695 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.8688. Min Act: -0.1699
Data Index: 2900694 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.8376. Min Act: -0.1700
Data Index: 4776951 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4313. Min Range: -7.4313
Max Act: 6.8376. Min Act: -0.1700
Data Index: 7320270 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19