Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1546 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.7063. Min Act: -0.1700
Data Index: 7433726 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.6126. Min Act: -0.1700
Data Index: 5533909 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.5501. Min Act: -0.1700
Data Index: 3438638 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.5188. Min Act: -0.1700
Data Index: 8359853 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.5188. Min Act: -0.1700
Data Index: 5649966 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.4251. Min Act: -0.1700
Data Index: 6243245 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.3001. Min Act: -0.1700
Data Index: 206759 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.2688. Min Act: -0.1700
Data Index: 5246242 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.2688. Min Act: -0.1700
Data Index: 7081899 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.2688. Min Act: -0.1700
Data Index: 5937620 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.2376. Min Act: -0.1700
Data Index: 4679394 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.2376. Min Act: -0.1700
Data Index: 4032212 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.1751. Min Act: -0.1700
Data Index: 3739940 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.1751. Min Act: -0.1700
Data Index: 1790267 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.1751. Min Act: -0.1700
Data Index: 4276343 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.1438. Min Act: -0.1700
Data Index: 6132469 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.1438. Min Act: -0.1700
Data Index: 273023 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.1126. Min Act: -0.1700
Data Index: 5618536 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.1126. Min Act: -0.1700
Data Index: 3207193 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7063. Min Range: -6.7063
Max Act: 6.1126. Min Act: -0.1700
Data Index: 4468063 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19