Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1002 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3817. Min Range: -8.3817
Max Act: 8.3817. Min Act: -0.1700
Data Index: 6084768 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.7880. Min Act: -0.1700
Data Index: 6266422 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.7255. Min Act: -0.1700
Data Index: 6068886 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.6317. Min Act: -0.1700
Data Index: 531872 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.6630. Min Act: -0.1700
Data Index: 160593 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.6317. Min Act: -0.1700
Data Index: 3202663 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.5692. Min Act: -0.1700
Data Index: 6586792 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.4755. Min Act: -0.1700
Data Index: 1457590 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.3817. Min Act: -0.1700
Data Index: 4723785 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.3505. Min Act: -0.1700
Data Index: 6226509 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.2880. Min Act: -0.1700
Data Index: 4335165 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.2567. Min Act: -0.1700
Data Index: 7496916 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.2255. Min Act: -0.1700
Data Index: 8461107 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.1630. Min Act: -0.1700
Data Index: 1356562 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.1630. Min Act: -0.1700
Data Index: 5576786 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.0692. Min Act: -0.1700
Data Index: 121146 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.1005. Min Act: -0.1700
Data Index: 4793841 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.0692. Min Act: -0.1700
Data Index: 1881406 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.0380. Min Act: -0.1700
Data Index: 404508 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3817. Min Range: -8.3817
Max Act: 7.0380. Min Act: -0.1700
Data Index: 1059537 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19