Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3969. Min Range: -7.3969
Max Act: 7.3969. Min Act: -0.1700
Data Index: 2457222 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3969. Min Range: -7.3969
Max Act: 7.2406. Min Act: -0.1700
Data Index: 1375546 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3969. Min Range: -7.3969
Max Act: 7.2094. Min Act: -0.1700
Data Index: 5047658 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3969. Min Range: -7.3969
Max Act: 7.1781. Min Act: -0.1700
Data Index: 7809674 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3969. Min Range: -7.3969
Max Act: 7.1469. Min Act: -0.1700
Data Index: 5881457 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3969. Min Range: -7.3969
Max Act: 7.0531. Min Act: -0.1700
Data Index: 164612 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3969. Min Range: -7.3969
Max Act: 7.0219. Min Act: -0.1700
Data Index: 5040435 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3969. Min Range: -7.3969
Max Act: 7.0219. Min Act: -0.1700
Data Index: 937820 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.9594. Min Act: -0.1700
Data Index: 3185092 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.9594. Min Act: -0.1700
Data Index: 249604 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.9281. Min Act: -0.1700
Data Index: 4830920 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.9281. Min Act: -0.1700
Data Index: 8242921 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.8969. Min Act: -0.1700
Data Index: 1368536 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.8969. Min Act: -0.1700
Data Index: 5287709 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.8656. Min Act: -0.1700
Data Index: 6021234 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.8344. Min Act: -0.1700
Data Index: 5861009 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.8031. Min Act: -0.1700
Data Index: 3211041 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.7719. Min Act: -0.1700
Data Index: 6456820 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.7719. Min Act: -0.1700
Data Index: 5675863 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3969. Min Range: -7.3969
Max Act: 6.7406. Min Act: -0.1700
Data Index: 1758973 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19