Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3128. Min Range: -7.3128
Max Act: 7.3128. Min Act: -0.1683
Data Index: 890339 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3128. Min Range: -7.3128
Max Act: 7.0003. Min Act: -0.1178
Data Index: 6652240 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.9690. Min Act: -0.1553
Data Index: 4890011 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.8753. Min Act: -0.1641
Data Index: 890338 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.8128. Min Act: -0.1700
Data Index: 4570190 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.7815. Min Act: -0.1014
Data Index: 3211320 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.7815. Min Act: -0.1700
Data Index: 7571882 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.7503. Min Act: -0.1216
Data Index: 4890012 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.7503. Min Act: -0.1211
Data Index: 1967867 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.7190. Min Act: -0.1651
Data Index: 1141770 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.6878. Min Act: -0.1700
Data Index: 4503059 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.6565. Min Act: -0.1700
Data Index: 6856191 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.5940. Min Act: -0.1687
Data Index: 5373708 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.5940. Min Act: -0.1700
Data Index: 6652241 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.5628. Min Act: -0.1700
Data Index: 1777687 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.5628. Min Act: -0.1700
Data Index: 4570189 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.5315. Min Act: -0.1696
Data Index: 6225711 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.5315. Min Act: -0.1700
Data Index: 8445528 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.5315. Min Act: -0.1700
Data Index: 4772708 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3128. Min Range: -7.3128
Max Act: 6.5315. Min Act: -0.1700
Data Index: 2337221 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19