Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2045. Min Range: -6.2045
Max Act: 6.2045. Min Act: -0.1700
Data Index: 5776041 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.9545. Min Act: -0.1700
Data Index: 7594447 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.9232. Min Act: -0.1700
Data Index: 6235635 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.8607. Min Act: -0.1700
Data Index: 4781779 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.7982. Min Act: -0.1700
Data Index: 1087403 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.7357. Min Act: -0.1700
Data Index: 3068475 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.7045. Min Act: -0.1700
Data Index: 5203074 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.7357. Min Act: -0.1700
Data Index: 3815821 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.6420. Min Act: -0.1700
Data Index: 8033212 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.6420. Min Act: -0.1700
Data Index: 6053969 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.6420. Min Act: -0.1700
Data Index: 7083087 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.6732. Min Act: -0.1700
Data Index: 6715876 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.5795. Min Act: -0.1700
Data Index: 3558000 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.5482. Min Act: -0.1700
Data Index: 4335023 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.5795. Min Act: -0.1700
Data Index: 265678 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.6107. Min Act: -0.1700
Data Index: 6254128 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.6107. Min Act: -0.1700
Data Index: 1302733 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.5795. Min Act: -0.1700
Data Index: 7539775 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.5795. Min Act: -0.1700
Data Index: 3724859 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2045. Min Range: -6.2045
Max Act: 5.5482. Min Act: -0.1700
Data Index: 4947943 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19