Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3413 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3102. Min Range: -7.3102
Max Act: 7.3102. Min Act: -0.1700
Data Index: 7893699 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3102. Min Range: -7.3102
Max Act: 7.0289. Min Act: -0.1700
Data Index: 7953146 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.9664. Min Act: -0.1700
Data Index: 6290514 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.9039. Min Act: -0.1700
Data Index: 4346301 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8727. Min Act: -0.1700
Data Index: 6562975 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8414. Min Act: -0.1700
Data Index: 2990109 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8727. Min Act: -0.1700
Data Index: 3802030 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8414. Min Act: -0.1700
Data Index: 7253238 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.7164. Min Act: -0.1700
Data Index: 8280093 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.7164. Min Act: -0.1700
Data Index: 5809342 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6852. Min Act: -0.1700
Data Index: 2144562 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6852. Min Act: -0.1700
Data Index: 5914223 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6852. Min Act: -0.1700
Data Index: 6676388 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6539. Min Act: -0.1700
Data Index: 3858001 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6852. Min Act: -0.1700
Data Index: 6080527 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6852. Min Act: -0.1700
Data Index: 4810829 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6227. Min Act: -0.1700
Data Index: 3481255 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6227. Min Act: -0.1700
Data Index: 4662718 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6227. Min Act: -0.1700
Data Index: 1963621 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6227. Min Act: -0.1700
Data Index: 3171896 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19