Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1909 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.5274. Min Act: -0.1700
Data Index: 4887484 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.5274. Min Act: -0.1700
Data Index: 4520037 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.4337. Min Act: -0.1700
Data Index: 5949192 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.3712. Min Act: -0.1700
Data Index: 3928517 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.3712. Min Act: -0.1700
Data Index: 1474802 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.3087. Min Act: -0.1700
Data Index: 706508 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.2774. Min Act: -0.1700
Data Index: 7243975 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.2774. Min Act: -0.1700
Data Index: 6313669 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.2149. Min Act: -0.1700
Data Index: 6038254 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.1837. Min Act: -0.1700
Data Index: 4009693 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.1524. Min Act: -0.1700
Data Index: 8106221 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.1212. Min Act: -0.1700
Data Index: 2242345 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.0899. Min Act: -0.1700
Data Index: 799714 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.0899. Min Act: -0.1700
Data Index: 870024 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.0587. Min Act: -0.1700
Data Index: 8724267 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.0274. Min Act: -0.1700
Data Index: 6532662 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.0274. Min Act: -0.1700
Data Index: 5670716 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.0899. Min Act: -0.1700
Data Index: 6563781 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.0274. Min Act: -0.1700
Data Index: 4714343 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5274. Min Range: -6.5274
Max Act: 6.0274. Min Act: -0.1700
Data Index: 7428831 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19