Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.9201. Min Act: -0.1700
Data Index: 6023732 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.8889. Min Act: -0.1700
Data Index: 7183696 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.8264. Min Act: -0.1700
Data Index: 7994800 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.8264. Min Act: -0.1700
Data Index: 8686834 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.7951. Min Act: -0.1700
Data Index: 3767212 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.7639. Min Act: -0.1700
Data Index: 1491023 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.7639. Min Act: -0.1700
Data Index: 5093905 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.7639. Min Act: -0.1700
Data Index: 648859 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.7326. Min Act: -0.1700
Data Index: 6210589 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.7014. Min Act: -0.1700
Data Index: 402526 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.7326. Min Act: -0.1700
Data Index: 6105035 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.7014. Min Act: -0.1700
Data Index: 3157097 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.6389. Min Act: -0.1700
Data Index: 3990820 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.6701. Min Act: -0.1700
Data Index: 5488582 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.6701. Min Act: -0.1700
Data Index: 8757121 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.5764. Min Act: -0.1700
Data Index: 7062435 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.5764. Min Act: -0.1700
Data Index: 1459768 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.5139. Min Act: -0.1700
Data Index: 4030273 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.5451. Min Act: -0.1700
Data Index: 7295224 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9201. Min Range: -6.9201
Max Act: 6.4826. Min Act: -0.1700
Data Index: 1369308 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19