Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4714 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1734. Min Range: -12.1734
Max Act: 12.1734. Min Act: -0.1700
Data Index: 4543810 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.9234. Min Act: -0.1700
Data Index: 5449564 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.7984. Min Act: -0.1700
Data Index: 6469946 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.6734. Min Act: -0.1700
Data Index: 5561442 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.6734. Min Act: -0.1700
Data Index: 8566668 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.6734. Min Act: -0.1700
Data Index: 4560404 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.6734. Min Act: -0.1700
Data Index: 7121488 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.6734. Min Act: -0.1700
Data Index: 8410435 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.6109. Min Act: -0.1700
Data Index: 7676036 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.6109. Min Act: -0.1700
Data Index: 1026024 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.6109. Min Act: -0.1700
Data Index: 1936373 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.6109. Min Act: -0.1700
Data Index: 6226180 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.5484. Min Act: -0.1700
Data Index: 3504957 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.4234. Min Act: -0.1700
Data Index: 5572267 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.4859. Min Act: -0.1700
Data Index: 2754252 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.4859. Min Act: -0.1700
Data Index: 1904123 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.4234. Min Act: -0.1700
Data Index: 7513710 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.4859. Min Act: -0.1700
Data Index: 6966072 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.4234. Min Act: -0.1700
Data Index: 2803576 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1734. Min Range: -12.1734
Max Act: 11.4859. Min Act: -0.1700
Data Index: 3751270 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19