Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 682 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.6242. Min Act: -0.1700
Data Index: 8691954 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.5304. Min Act: -0.1700
Data Index: 2990628 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.4992. Min Act: -0.1700
Data Index: 6127835 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.4679. Min Act: -0.1700
Data Index: 6217662 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.4679. Min Act: -0.1700
Data Index: 2446813 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.4367. Min Act: -0.1700
Data Index: 4167034 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.2804. Min Act: -0.1700
Data Index: 33765 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.2804. Min Act: -0.1700
Data Index: 5853056 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.2492. Min Act: -0.1700
Data Index: 2195330 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.2492. Min Act: -0.1700
Data Index: 4629962 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.1867. Min Act: -0.1700
Data Index: 113187 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.1867. Min Act: -0.1700
Data Index: 5869939 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.1867. Min Act: -0.1700
Data Index: 162547 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.1867. Min Act: -0.1700
Data Index: 5497375 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.1242. Min Act: -0.1700
Data Index: 8223850 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.0304. Min Act: -0.1700
Data Index: 3997461 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.0617. Min Act: -0.1700
Data Index: 8613054 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.0617. Min Act: -0.1700
Data Index: 5817785 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.0617. Min Act: -0.1700
Data Index: 4529010 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6242. Min Range: -6.6242
Max Act: 6.0304. Min Act: -0.1700
Data Index: 3883008 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19