Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.6522. Min Act: -0.1700
Data Index: 2193643 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.6834. Min Act: -0.1700
Data Index: 793196 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.6209. Min Act: -0.1700
Data Index: 3517026 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.5584. Min Act: -0.1700
Data Index: 6892123 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.5584. Min Act: -0.1700
Data Index: 5836852 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.4647. Min Act: -0.1700
Data Index: 3714155 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.3709. Min Act: -0.1700
Data Index: 7520680 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.3709. Min Act: -0.1700
Data Index: 3397562 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.3709. Min Act: -0.1700
Data Index: 1786585 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.3397. Min Act: -0.1700
Data Index: 709640 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.2772. Min Act: -0.1700
Data Index: 549931 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.3084. Min Act: -0.1700
Data Index: 8826194 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.3084. Min Act: -0.1700
Data Index: 2867795 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.3084. Min Act: -0.1700
Data Index: 2132208 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.3084. Min Act: -0.1700
Data Index: 129071 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.2772. Min Act: -0.1700
Data Index: 7698247 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.2772. Min Act: -0.1700
Data Index: 763752 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.2459. Min Act: -0.1700
Data Index: 3131171 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.2772. Min Act: -0.1700
Data Index: 3440454 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6834. Min Range: -6.6834
Max Act: 6.2147. Min Act: -0.1700
Data Index: 7786166 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19