Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 753 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3635. Min Act: -0.1700
Data Index: 6010200 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3635. Min Act: -0.1700
Data Index: 8657117 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3322. Min Act: -0.1700
Data Index: 397792 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 4599856 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3322. Min Act: -0.1700
Data Index: 4385653 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3322. Min Act: -0.1700
Data Index: 474422 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3322. Min Act: -0.1700
Data Index: 464941 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3322. Min Act: -0.1700
Data Index: 5760517 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3322. Min Act: -0.1700
Data Index: 7945612 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3322. Min Act: -0.1700
Data Index: 7788928 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3322. Min Act: -0.1700
Data Index: 7053600 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 933808 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3322. Min Act: -0.1700
Data Index: 5767109 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 3417420 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 1350344 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 3757644 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 3915545 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 4038771 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 529816 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3635. Min Range: -4.3635
Max Act: 4.3010. Min Act: -0.1700
Data Index: 690307 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19