Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5410. Min Range: -6.5410
Max Act: 6.5410. Min Act: -0.1700
Data Index: 7240919 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5410. Min Range: -6.5410
Max Act: 6.3223. Min Act: -0.1700
Data Index: 7970696 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5410. Min Range: -6.5410
Max Act: 6.2598. Min Act: -0.1700
Data Index: 2727892 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5410. Min Range: -6.5410
Max Act: 6.0098. Min Act: -0.1700
Data Index: 2141792 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5410. Min Range: -6.5410
Max Act: 6.0098. Min Act: -0.1700
Data Index: 2921879 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5410. Min Range: -6.5410
Max Act: 6.0098. Min Act: -0.1700
Data Index: 6580568 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5410. Min Range: -6.5410
Max Act: 6.0098. Min Act: -0.1700
Data Index: 4007063 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5410. Min Range: -6.5410
Max Act: 6.0410. Min Act: -0.1700
Data Index: 1430291 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.9785. Min Act: -0.1700
Data Index: 5648854 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.9473. Min Act: -0.1700
Data Index: 6655138 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.9473. Min Act: -0.1700
Data Index: 6576963 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.9160. Min Act: -0.1700
Data Index: 1985952 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.9160. Min Act: -0.1700
Data Index: 6179339 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.8535. Min Act: -0.1700
Data Index: 1844685 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.8223. Min Act: -0.1700
Data Index: 7501548 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.8535. Min Act: -0.1700
Data Index: 678189 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.8223. Min Act: -0.1700
Data Index: 5883528 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.8223. Min Act: -0.1700
Data Index: 4085445 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.8223. Min Act: -0.1700
Data Index: 5400177 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5410. Min Range: -6.5410
Max Act: 5.8223. Min Act: -0.1700
Data Index: 6501683 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19