Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5851. Min Range: -8.5851
Max Act: 8.5851. Min Act: -0.1700
Data Index: 478978 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5851. Min Range: -8.5851
Max Act: 8.2101. Min Act: -0.1700
Data Index: 478979 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.9914. Min Act: -0.1700
Data Index: 6414308 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.8664. Min Act: -0.1700
Data Index: 7672328 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.7101. Min Act: -0.1700
Data Index: 2245788 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.6476. Min Act: -0.1700
Data Index: 6765595 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.5226. Min Act: -0.1700
Data Index: 4258258 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.4601. Min Act: -0.1700
Data Index: 3334686 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.3976. Min Act: -0.1700
Data Index: 1915109 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.3351. Min Act: -0.1700
Data Index: 3165479 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.3351. Min Act: -0.1700
Data Index: 3918631 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.2414. Min Act: -0.1700
Data Index: 2511364 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.1789. Min Act: -0.1700
Data Index: 1915110 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.1476. Min Act: -0.1700
Data Index: 6509304 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.1476. Min Act: -0.1700
Data Index: 7689439 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.0851. Min Act: -0.1700
Data Index: 2543441 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.0851. Min Act: -0.1700
Data Index: 638370 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.0851. Min Act: -0.1700
Data Index: 478982 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.0851. Min Act: -0.1700
Data Index: 4013735 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5851. Min Range: -8.5851
Max Act: 7.0851. Min Act: -0.1700
Data Index: 2000093 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19