Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4212 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.8735. Min Act: -0.1700
Data Index: 6344123 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.8110. Min Act: -0.1700
Data Index: 5523884 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7485. Min Act: -0.1700
Data Index: 8446820 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.8110. Min Act: -0.1700
Data Index: 7843259 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7485. Min Act: -0.1700
Data Index: 2756919 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7485. Min Act: -0.1700
Data Index: 4612495 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7797. Min Act: -0.1700
Data Index: 6819726 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7797. Min Act: -0.1700
Data Index: 94535 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7485. Min Act: -0.1700
Data Index: 7269675 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.6860. Min Act: -0.1700
Data Index: 2415282 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7485. Min Act: -0.1700
Data Index: 7280848 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7172. Min Act: -0.1700
Data Index: 2937671 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.6860. Min Act: -0.1700
Data Index: 2293414 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.6860. Min Act: -0.1700
Data Index: 6949703 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7172. Min Act: -0.1700
Data Index: 7199298 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.6860. Min Act: -0.1700
Data Index: 1997508 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.6860. Min Act: -0.1700
Data Index: 6691336 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.6860. Min Act: -0.1700
Data Index: 6212041 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.6860. Min Act: -0.1700
Data Index: 1104984 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.6547. Min Act: -0.1700
Data Index: 1081039 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19