Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3852 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.9867. Min Act: -0.1700
Data Index: 7275875 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.9242. Min Act: -0.1700
Data Index: 545461 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.8305. Min Act: -0.1700
Data Index: 517031 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7992. Min Act: -0.1700
Data Index: 3503498 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7680. Min Act: -0.1700
Data Index: 7472044 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.6742. Min Act: -0.1700
Data Index: 4698067 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.6117. Min Act: -0.1700
Data Index: 4456503 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.6117. Min Act: -0.1700
Data Index: 5466167 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.6117. Min Act: -0.1700
Data Index: 6341770 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.5805. Min Act: -0.1700
Data Index: 6893739 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.6117. Min Act: -0.1700
Data Index: 6834909 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.5805. Min Act: -0.1700
Data Index: 7382764 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.5805. Min Act: -0.1700
Data Index: 2755557 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.5805. Min Act: -0.1700
Data Index: 6140731 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.5805. Min Act: -0.1700
Data Index: 3682808 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.5492. Min Act: -0.1700
Data Index: 6402492 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.5180. Min Act: -0.1700
Data Index: 46308 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.5180. Min Act: -0.1700
Data Index: 7217335 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.5180. Min Act: -0.1700
Data Index: 634170 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.4555. Min Act: -0.1700
Data Index: 3291204 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19