Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4369 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.9191. Min Act: -0.1700
Data Index: 6951446 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.7941. Min Act: -0.1700
Data Index: 1735411 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.7316. Min Act: -0.1700
Data Index: 7014770 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.7316. Min Act: -0.1700
Data Index: 2085008 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.6691. Min Act: -0.1700
Data Index: 79387 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.6691. Min Act: -0.1700
Data Index: 3977262 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.6066. Min Act: -0.1700
Data Index: 5003910 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.5441. Min Act: -0.1700
Data Index: 487830 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.5441. Min Act: -0.1700
Data Index: 2010009 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.5441. Min Act: -0.1700
Data Index: 1785683 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 8435715 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 3899120 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 7244291 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 4986439 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 771695 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4191. Min Act: -0.1700
Data Index: 8101272 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4191. Min Act: -0.1700
Data Index: 7719519 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4191. Min Act: -0.1700
Data Index: 4607666 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4191. Min Act: -0.1700
Data Index: 904765 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9191. Min Range: -10.9191
Max Act: 10.4191. Min Act: -0.1700
Data Index: 7154851 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19