Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.6953. Min Act: -0.1700
Data Index: 5227499 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.7266. Min Act: -0.1700
Data Index: 956808 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.6953. Min Act: -0.1700
Data Index: 8085658 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.6328. Min Act: -0.1700
Data Index: 5371456 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.6328. Min Act: -0.1700
Data Index: 2029116 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.6016. Min Act: -0.1700
Data Index: 1667255 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.6016. Min Act: -0.1700
Data Index: 4386563 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 7444511 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5703. Min Act: -0.1700
Data Index: 3536528 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 6227991 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 4415982 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 4398154 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 7375411 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5078. Min Act: -0.1700
Data Index: 373245 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 4985916 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 7063587 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 3732795 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 5227498 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5391. Min Act: -0.1700
Data Index: 3626503 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7266. Min Range: -6.7266
Max Act: 6.5078. Min Act: -0.1700
Data Index: 4393905 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19