Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6391 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.7002. Min Act: -0.1700
Data Index: 3616586 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.7315. Min Act: -0.1700
Data Index: 2565116 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.6690. Min Act: -0.1700
Data Index: 6134183 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.5127. Min Act: -0.1700
Data Index: 3339893 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.4815. Min Act: -0.1700
Data Index: 5913277 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.4190. Min Act: -0.1700
Data Index: 7005535 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.4190. Min Act: -0.1700
Data Index: 4972581 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.4190. Min Act: -0.1700
Data Index: 889039 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.3252. Min Act: -0.1694
Data Index: 998412 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.3252. Min Act: -0.1700
Data Index: 4394665 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.3252. Min Act: -0.1700
Data Index: 4093061 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.2315. Min Act: -0.1700
Data Index: 1199144 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.2002. Min Act: -0.1700
Data Index: 4955068 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.1690. Min Act: -0.1700
Data Index: 2052961 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.1377. Min Act: -0.1700
Data Index: 1000720 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.1065. Min Act: -0.1700
Data Index: 755027 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.1065. Min Act: -0.1700
Data Index: 4983407 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.1065. Min Act: -0.1700
Data Index: 588222 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.1377. Min Act: -0.1700
Data Index: 412711 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7315. Min Range: -7.7315
Max Act: 7.1065. Min Act: -0.1700
Data Index: 4080880 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19