Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0076. Min Range: -8.0076
Max Act: 8.0076. Min Act: -0.1700
Data Index: 1902390 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.9451. Min Act: -0.1700
Data Index: 277352 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.8826. Min Act: -0.1700
Data Index: 1854558 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.8514. Min Act: -0.1700
Data Index: 5828637 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.6951. Min Act: -0.1700
Data Index: 4263374 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.6951. Min Act: -0.1700
Data Index: 6220877 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.6639. Min Act: -0.1700
Data Index: 4054505 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.6014. Min Act: -0.1700
Data Index: 678863 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.5701. Min Act: -0.1700
Data Index: 4699353 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.5701. Min Act: -0.1700
Data Index: 4337048 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.5389. Min Act: -0.1700
Data Index: 4648035 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.5389. Min Act: -0.1700
Data Index: 3600380 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.5076. Min Act: -0.1700
Data Index: 6408729 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.5076. Min Act: -0.1700
Data Index: 1074452 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.5389. Min Act: -0.1700
Data Index: 1788749 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.5389. Min Act: -0.1700
Data Index: 795527 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.4451. Min Act: -0.1700
Data Index: 6456503 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.4139. Min Act: -0.1700
Data Index: 4963726 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.4139. Min Act: -0.1700
Data Index: 7918328 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0076. Min Range: -8.0076
Max Act: 7.4139. Min Act: -0.1700
Data Index: 1384188 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19