Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2121. Min Range: -8.2121
Max Act: 8.2121. Min Act: -0.1700
Data Index: 284622 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.9621. Min Act: -0.1700
Data Index: 1678618 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.8996. Min Act: -0.1700
Data Index: 1532990 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.7433. Min Act: -0.1700
Data Index: 7445737 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.7121. Min Act: -0.1700
Data Index: 1934034 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.6808. Min Act: -0.1700
Data Index: 8507226 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.6496. Min Act: -0.1700
Data Index: 4177899 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.6183. Min Act: -0.1700
Data Index: 2727768 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.5871. Min Act: -0.1700
Data Index: 1503656 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4933. Min Act: -0.1700
Data Index: 2403662 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4933. Min Act: -0.1700
Data Index: 599319 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4933. Min Act: -0.1700
Data Index: 554134 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4621. Min Act: -0.1700
Data Index: 8554466 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4621. Min Act: -0.1700
Data Index: 3959373 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4621. Min Act: -0.1700
Data Index: 4048128 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4621. Min Act: -0.1700
Data Index: 972975 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4621. Min Act: -0.1700
Data Index: 5262529 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4308. Min Act: -0.1700
Data Index: 385803 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.4308. Min Act: -0.1700
Data Index: 1909879 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2121. Min Range: -8.2121
Max Act: 7.3996. Min Act: -0.1700
Data Index: 4257872 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19