Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4527 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.8596. Min Act: -0.1700
Data Index: 5947898 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.8596. Min Act: -0.1700
Data Index: 8041136 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.7971. Min Act: -0.1700
Data Index: 1921958 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.7659. Min Act: -0.1700
Data Index: 564771 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.7659. Min Act: -0.1700
Data Index: 2433496 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.6721. Min Act: -0.1700
Data Index: 4296710 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.6409. Min Act: -0.1700
Data Index: 89452 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.6096. Min Act: -0.1700
Data Index: 942497 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.6096. Min Act: -0.1700
Data Index: 4328846 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.6096. Min Act: -0.1700
Data Index: 8687317 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.5784. Min Act: -0.1700
Data Index: 5143080 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.5784. Min Act: -0.1700
Data Index: 2493977 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.5784. Min Act: -0.1700
Data Index: 3783378 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.5784. Min Act: -0.1700
Data Index: 6296037 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.5471. Min Act: -0.1700
Data Index: 5496099 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.5471. Min Act: -0.1700
Data Index: 6576776 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.5784. Min Act: -0.1700
Data Index: 2644726 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.5784. Min Act: -0.1700
Data Index: 2501224 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.5471. Min Act: -0.1700
Data Index: 5860767 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8596. Min Range: -4.8596
Max Act: 4.4846. Min Act: -0.1700
Data Index: 4678323 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19