Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.6569. Min Act: -0.1700
Data Index: 7630136 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.4069. Min Act: -0.1700
Data Index: 3097555 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.4382. Min Act: -0.1700
Data Index: 8410559 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.4382. Min Act: -0.1700
Data Index: 8230616 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.4382. Min Act: -0.1700
Data Index: 5302910 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.4382. Min Act: -0.1700
Data Index: 3436895 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.4069. Min Act: -0.1700
Data Index: 7129762 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.4069. Min Act: -0.1700
Data Index: 1866686 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.3757. Min Act: -0.1700
Data Index: 287583 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.3444. Min Act: -0.1700
Data Index: 195611 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.3757. Min Act: -0.1700
Data Index: 273969 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.3757. Min Act: -0.1700
Data Index: 7151896 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.3132. Min Act: -0.1700
Data Index: 1949788 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.3132. Min Act: -0.1700
Data Index: 1866683 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.2819. Min Act: -0.1700
Data Index: 1739801 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.2819. Min Act: -0.1700
Data Index: 5476834 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.3132. Min Act: -0.1700
Data Index: 1268250 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.2819. Min Act: -0.1700
Data Index: 4844661 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.2819. Min Act: -0.1700
Data Index: 3949185 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6569. Min Range: -5.6569
Max Act: 5.2507. Min Act: -0.1700
Data Index: 4127466 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19