Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.8469. Min Act: -0.1700
Data Index: 6084625 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.7061. Min Act: -0.1700
Data Index: 4508453 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.6435. Min Act: -0.1700
Data Index: 3609098 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.6279. Min Act: -0.1700
Data Index: 1843766 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.6435. Min Act: -0.1700
Data Index: 2603676 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.6122. Min Act: -0.1700
Data Index: 5330335 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5966. Min Act: -0.1700
Data Index: 306791 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5809. Min Act: -0.1700
Data Index: 7230291 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5809. Min Act: -0.1700
Data Index: 1139330 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5966. Min Act: -0.1700
Data Index: 3584419 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5809. Min Act: -0.1700
Data Index: 6266723 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5496. Min Act: -0.1700
Data Index: 8392153 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5340. Min Act: -0.1700
Data Index: 520362 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5183. Min Act: -0.1700
Data Index: 8729317 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5340. Min Act: -0.1700
Data Index: 6711882 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5340. Min Act: -0.1700
Data Index: 7659700 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5340. Min Act: -0.1700
Data Index: 2924287 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5183. Min Act: -0.1700
Data Index: 7605645 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5183. Min Act: -0.1700
Data Index: 2659557 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8469. Min Range: -3.8469
Max Act: 3.5183. Min Act: -0.1700
Data Index: 5255270 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19