Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1289 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9473. Min Range: -4.9473
Max Act: 4.9473. Min Act: -0.1700
Data Index: 6396205 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9473. Min Range: -4.9473
Max Act: 4.6036. Min Act: -0.1700
Data Index: 7909667 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9473. Min Range: -4.9473
Max Act: 4.5098. Min Act: -0.1700
Data Index: 5719113 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9473. Min Range: -4.9473
Max Act: 4.1661. Min Act: -0.1700
Data Index: 1406936 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9473. Min Range: -4.9473
Max Act: 4.0723. Min Act: -0.1700
Data Index: 3963537 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9473. Min Range: -4.9473
Max Act: 4.0567. Min Act: -0.1700
Data Index: 5147518 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.9473. Min Act: -0.1700
Data Index: 6102625 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.9629. Min Act: -0.1700
Data Index: 6113546 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.8222. Min Act: -0.1700
Data Index: 2787031 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.8535. Min Act: -0.1700
Data Index: 962386 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.7753. Min Act: -0.1700
Data Index: 4947691 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.7284. Min Act: -0.1700
Data Index: 1977266 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.7753. Min Act: -0.1700
Data Index: 962856 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.7596. Min Act: -0.1700
Data Index: 5640507 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.7909. Min Act: -0.1700
Data Index: 6515158 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.7284. Min Act: -0.1700
Data Index: 7654451 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.8222. Min Act: -0.1700
Data Index: 4864835 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.7127. Min Act: -0.1700
Data Index: 3698499 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.7284. Min Act: -0.1700
Data Index: 7172296 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9473. Min Range: -4.9473
Max Act: 3.6971. Min Act: -0.1700
Data Index: 2216568 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19