Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.9477. Min Act: -0.1700
Data Index: 4946781 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.7915. Min Act: -0.1700
Data Index: 6329549 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.7915. Min Act: -0.1700
Data Index: 1578836 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6383232 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.7290. Min Act: -0.1700
Data Index: 5650169 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.7290. Min Act: -0.1700
Data Index: 7868575 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.7290. Min Act: -0.1700
Data Index: 7379995 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.7290. Min Act: -0.1700
Data Index: 1276212 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6977. Min Act: -0.1700
Data Index: 153296 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6665. Min Act: -0.1700
Data Index: 6670047 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6665. Min Act: -0.1700
Data Index: 1456104 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6665. Min Act: -0.1700
Data Index: 3226847 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6665. Min Act: -0.1700
Data Index: 1599833 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6352. Min Act: -0.1700
Data Index: 5110362 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6352. Min Act: -0.1700
Data Index: 1927881 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6352. Min Act: -0.1700
Data Index: 5664660 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6352. Min Act: -0.1700
Data Index: 6803128 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6040. Min Act: -0.1700
Data Index: 1920861 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.6040. Min Act: -0.1700
Data Index: 1348753 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9477. Min Range: -5.9477
Max Act: 5.5727. Min Act: -0.1700
Data Index: 2193650 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19