Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2034. Min Range: -10.2034
Max Act: 10.2034. Min Act: -0.1700
Data Index: 4444455 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2034. Min Range: -10.2034
Max Act: 10.1409. Min Act: -0.1700
Data Index: 378599 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2034. Min Range: -10.2034
Max Act: 10.0784. Min Act: -0.1700
Data Index: 7751636 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.8909. Min Act: -0.1700
Data Index: 726722 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.8284. Min Act: -0.1700
Data Index: 3331308 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.8909. Min Act: -0.1700
Data Index: 7436514 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.7659. Min Act: -0.1700
Data Index: 5603692 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.7659. Min Act: -0.1700
Data Index: 4554525 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.7659. Min Act: -0.1700
Data Index: 3765169 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.7034. Min Act: -0.1700
Data Index: 5195913 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.6409. Min Act: -0.1700
Data Index: 4440509 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.6409. Min Act: -0.1700
Data Index: 2468962 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.6409. Min Act: -0.1700
Data Index: 2944887 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.6409. Min Act: -0.1700
Data Index: 6077034 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.5784. Min Act: -0.1700
Data Index: 3197993 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.5784. Min Act: -0.1700
Data Index: 7169246 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.5784. Min Act: -0.1700
Data Index: 6812009 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.5784. Min Act: -0.1700
Data Index: 6382972 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.5784. Min Act: -0.1698
Data Index: 5312380 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2034. Min Range: -10.2034
Max Act: 9.5159. Min Act: -0.1700
Data Index: 5805716 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19