Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6392 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0459. Min Range: -9.0459
Max Act: 9.0459. Min Act: -0.1700
Data Index: 7381878 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.7959. Min Act: -0.1700
Data Index: 4198013 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.7959. Min Act: -0.1700
Data Index: 8713612 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.6709. Min Act: -0.1700
Data Index: 6938810 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.6709. Min Act: -0.1700
Data Index: 366005 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.6084. Min Act: -0.1700
Data Index: 1531325 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.4834. Min Act: -0.1700
Data Index: 8387281 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.4209. Min Act: -0.1700
Data Index: 3161725 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.4209. Min Act: -0.1700
Data Index: 8638062 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.3584. Min Act: -0.1700
Data Index: 5590739 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.3584. Min Act: -0.1700
Data Index: 4970464 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.2959. Min Act: -0.1700
Data Index: 169635 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.2959. Min Act: -0.1700
Data Index: 6134210 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.1709. Min Act: -0.1700
Data Index: 4269425 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.2334. Min Act: -0.1700
Data Index: 8416498 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.2334. Min Act: -0.1700
Data Index: 351919 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.2334. Min Act: -0.1700
Data Index: 809441 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.1709. Min Act: -0.1700
Data Index: 1754242 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.1709. Min Act: -0.1700
Data Index: 7251510 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0459. Min Range: -9.0459
Max Act: 8.1084. Min Act: -0.1700
Data Index: 516264 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19