Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.9896. Min Act: -0.1700
Data Index: 1192668 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.8958. Min Act: -0.1700
Data Index: 6722564 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.8646. Min Act: -0.1700
Data Index: 5246045 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.8646. Min Act: -0.1700
Data Index: 5256564 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.8333. Min Act: -0.1700
Data Index: 5207295 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.7396. Min Act: -0.1700
Data Index: 5985604 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.7396. Min Act: -0.1700
Data Index: 4730505 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.6458. Min Act: -0.1700
Data Index: 1228603 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.6458. Min Act: -0.1700
Data Index: 7455389 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.6146. Min Act: -0.1700
Data Index: 7238535 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.5521. Min Act: -0.1700
Data Index: 3471348 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.5521. Min Act: -0.1700
Data Index: 555438 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.5521. Min Act: -0.1700
Data Index: 5479580 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.5521. Min Act: -0.1700
Data Index: 5001984 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.5208. Min Act: -0.1700
Data Index: 2151344 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.5208. Min Act: -0.1700
Data Index: 2557965 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.4896. Min Act: -0.1700
Data Index: 6140657 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.4896. Min Act: -0.1700
Data Index: 4078931 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.5208. Min Act: -0.1700
Data Index: 5881255 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9896. Min Range: -7.9896
Max Act: 7.4896. Min Act: -0.1700
Data Index: 6245995 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19