Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.7473. Min Act: -0.1700
Data Index: 2948464 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.6848. Min Act: -0.1700
Data Index: 8290586 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.4973. Min Act: -0.1700
Data Index: 7465604 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.5285. Min Act: -0.1700
Data Index: 1509125 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.4973. Min Act: -0.1700
Data Index: 7969906 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.4035. Min Act: -0.1700
Data Index: 6577163 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.3098. Min Act: -0.1700
Data Index: 4925019 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.2473. Min Act: -0.1700
Data Index: 1711636 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.2785. Min Act: -0.1700
Data Index: 8680900 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.2473. Min Act: -0.1700
Data Index: 6512758 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.2785. Min Act: -0.1700
Data Index: 231677 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.2160. Min Act: -0.1700
Data Index: 1675311 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.2160. Min Act: -0.1700
Data Index: 3007280 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.1848. Min Act: -0.1700
Data Index: 5795569 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.1848. Min Act: -0.1700
Data Index: 6225231 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.1848. Min Act: -0.1700
Data Index: 7690631 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.1848. Min Act: -0.1700
Data Index: 5377722 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.1223. Min Act: -0.1700
Data Index: 8195148 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.1848. Min Act: -0.1700
Data Index: 7526512 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7473. Min Range: -6.7473
Max Act: 6.1535. Min Act: -0.1700
Data Index: 4003371 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19