Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 675 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5271. Min Range: -6.5271
Max Act: 6.5271. Min Act: -0.1700
Data Index: 779893 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5271. Min Range: -6.5271
Max Act: 6.3084. Min Act: -0.1700
Data Index: 5255402 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5271. Min Range: -6.5271
Max Act: 6.2771. Min Act: -0.1700
Data Index: 2912667 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5271. Min Range: -6.5271
Max Act: 6.2771. Min Act: -0.1700
Data Index: 1408653 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5271. Min Range: -6.5271
Max Act: 6.1209. Min Act: -0.1700
Data Index: 6326617 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5271. Min Range: -6.5271
Max Act: 6.0896. Min Act: -0.1700
Data Index: 1030769 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5271. Min Range: -6.5271
Max Act: 6.0584. Min Act: -0.1700
Data Index: 6895711 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5271. Min Range: -6.5271
Max Act: 6.0271. Min Act: -0.1700
Data Index: 6328956 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9959. Min Act: -0.1700
Data Index: 411971 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9646. Min Act: -0.1700
Data Index: 5305013 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9646. Min Act: -0.1700
Data Index: 4431837 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9334. Min Act: -0.1700
Data Index: 7855952 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9646. Min Act: -0.1700
Data Index: 680480 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9334. Min Act: -0.1700
Data Index: 5366339 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9646. Min Act: -0.1700
Data Index: 484473 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9021. Min Act: -0.1700
Data Index: 4260489 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9021. Min Act: -0.1700
Data Index: 3233346 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9021. Min Act: -0.1700
Data Index: 8787827 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.9021. Min Act: -0.1700
Data Index: 7570756 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5271. Min Range: -6.5271
Max Act: 5.8709. Min Act: -0.1700
Data Index: 1415584 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19