Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.6891. Min Act: -0.1700
Data Index: 5149939 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.6735. Min Act: -0.1700
Data Index: 600109 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.6109. Min Act: -0.1700
Data Index: 1468643 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.6422. Min Act: -0.1700
Data Index: 8247372 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5796. Min Act: -0.1700
Data Index: 2529479 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5639. Min Act: -0.1700
Data Index: 6146923 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5796. Min Act: -0.1700
Data Index: 1398415 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5639. Min Act: -0.1700
Data Index: 3313517 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5639. Min Act: -0.1700
Data Index: 1398413 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5483. Min Act: -0.1700
Data Index: 8005295 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5483. Min Act: -0.1700
Data Index: 3766237 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5483. Min Act: -0.1700
Data Index: 4426853 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5639. Min Act: -0.1700
Data Index: 4943517 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5326. Min Act: -0.1700
Data Index: 7731581 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5483. Min Act: -0.1700
Data Index: 8678114 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5169. Min Act: -0.1700
Data Index: 14142 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5013. Min Act: -0.1700
Data Index: 2290115 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5326. Min Act: -0.1700
Data Index: 1528433 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.5169. Min Act: -0.1700
Data Index: 5891798 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6891. Min Range: -3.6891
Max Act: 3.4856. Min Act: -0.1700
Data Index: 3090876 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19