Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.5914. Min Act: -0.1700
Data Index: 1180701 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4661. Min Act: -0.1700
Data Index: 7737654 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4505. Min Act: -0.1700
Data Index: 892098 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4348. Min Act: -0.1700
Data Index: 821852 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.3564. Min Act: -0.1700
Data Index: 6487146 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2779. Min Act: -0.1700
Data Index: 5293631 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2936. Min Act: -0.1700
Data Index: 3112144 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2622. Min Act: -0.1700
Data Index: 8438683 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2465. Min Act: -0.1700
Data Index: 7666161 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2465. Min Act: -0.1700
Data Index: 7824555 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2465. Min Act: -0.1700
Data Index: 8589212 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2151. Min Act: -0.1700
Data Index: 5771859 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2308. Min Act: -0.1700
Data Index: 2323679 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2308. Min Act: -0.1700
Data Index: 7263653 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2308. Min Act: -0.1700
Data Index: 3402660 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.1993. Min Act: -0.1700
Data Index: 961060 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.2151. Min Act: -0.1700
Data Index: 7076394 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.1993. Min Act: -0.1700
Data Index: 4515469 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.1993. Min Act: -0.1700
Data Index: 8338870 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.1993. Min Act: -0.1700
Data Index: 8686440 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19