Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.9681. Min Act: -0.1700
Data Index: 2749863 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.7806. Min Act: -0.1700
Data Index: 1414592 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.8431. Min Act: -0.1700
Data Index: 1230000 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.8431. Min Act: -0.1700
Data Index: 2831993 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.7806. Min Act: -0.1700
Data Index: 8080054 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.7494. Min Act: -0.1700
Data Index: 5965974 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.6556. Min Act: -0.1700
Data Index: 1803328 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.6556. Min Act: -0.1700
Data Index: 860879 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.6244. Min Act: -0.1700
Data Index: 7289665 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.6556. Min Act: -0.1700
Data Index: 8461600 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.6244. Min Act: -0.1700
Data Index: 4527706 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.5931. Min Act: -0.1700
Data Index: 8447605 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.5306. Min Act: -0.1700
Data Index: 3638361 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.5306. Min Act: -0.1700
Data Index: 2712891 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.4994. Min Act: -0.1700
Data Index: 7596815 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.4681. Min Act: -0.1700
Data Index: 3626428 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.4994. Min Act: -0.1700
Data Index: 6253779 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.4681. Min Act: -0.1700
Data Index: 1039987 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.4681. Min Act: -0.1700
Data Index: 1685203 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9681. Min Range: -7.9681
Max Act: 7.4994. Min Act: -0.1700
Data Index: 1520239 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19