Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4596. Min Range: -9.4596
Max Act: 9.4596. Min Act: -0.1700
Data Index: 8593184 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4596. Min Range: -9.4596
Max Act: 9.2096. Min Act: -0.1700
Data Index: 8212372 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4596. Min Range: -9.4596
Max Act: 9.0221. Min Act: -0.1700
Data Index: 5945281 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.9596. Min Act: -0.1700
Data Index: 2410972 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.8971. Min Act: -0.1700
Data Index: 4475876 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.8971. Min Act: -0.1700
Data Index: 2412595 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.8346. Min Act: -0.1700
Data Index: 411685 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.6471. Min Act: -0.1700
Data Index: 3858121 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.7096. Min Act: -0.1700
Data Index: 6517815 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.7096. Min Act: -0.1700
Data Index: 7942471 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.6471. Min Act: -0.1700
Data Index: 3878850 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.6471. Min Act: -0.1700
Data Index: 6175226 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.6471. Min Act: -0.1700
Data Index: 2101559 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.6471. Min Act: -0.1700
Data Index: 7818384 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.5846. Min Act: -0.1700
Data Index: 494427 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.5846. Min Act: -0.1700
Data Index: 2023156 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.6471. Min Act: -0.1700
Data Index: 6262784 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.5221. Min Act: -0.1700
Data Index: 83827 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.5221. Min Act: -0.1700
Data Index: 640809 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4596. Min Range: -9.4596
Max Act: 8.5221. Min Act: -0.1700
Data Index: 3875745 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19