Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1227 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2314. Min Range: -7.2314
Max Act: 7.2314. Min Act: -0.1700
Data Index: 5394594 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2314. Min Range: -7.2314
Max Act: 7.2002. Min Act: -0.1700
Data Index: 7291729 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2314. Min Range: -7.2314
Max Act: 7.1689. Min Act: -0.1700
Data Index: 6151383 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2314. Min Range: -7.2314
Max Act: 7.1377. Min Act: -0.1700
Data Index: 7099642 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2314. Min Range: -7.2314
Max Act: 7.0439. Min Act: -0.1700
Data Index: 1826540 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.9814. Min Act: -0.1700
Data Index: 1799116 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2314. Min Range: -7.2314
Max Act: 7.0127. Min Act: -0.1700
Data Index: 3164659 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.9814. Min Act: -0.1700
Data Index: 5922630 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.9502. Min Act: -0.1700
Data Index: 6202766 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.9814. Min Act: -0.1700
Data Index: 7862527 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.8877. Min Act: -0.1700
Data Index: 7703808 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.8877. Min Act: -0.1700
Data Index: 4191927 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.9189. Min Act: -0.1700
Data Index: 5883596 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.9502. Min Act: -0.1700
Data Index: 1049899 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.8564. Min Act: -0.1700
Data Index: 6480372 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.8877. Min Act: -0.1700
Data Index: 2898285 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.8877. Min Act: -0.1700
Data Index: 229860 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.8877. Min Act: -0.1700
Data Index: 1892500 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.8877. Min Act: -0.1700
Data Index: 851936 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2314. Min Range: -7.2314
Max Act: 6.8564. Min Act: -0.1700
Data Index: 7098728 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19