Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.5090. Min Act: -0.1700
Data Index: 8555390 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.4778. Min Act: -0.1700
Data Index: 800872 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.3528. Min Act: -0.1700
Data Index: 3925885 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.3840. Min Act: -0.1700
Data Index: 4560534 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.2903. Min Act: -0.1700
Data Index: 5731562 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.2903. Min Act: -0.1700
Data Index: 1377882 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.2590. Min Act: -0.1700
Data Index: 5008130 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.2590. Min Act: -0.1700
Data Index: 2673391 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.2278. Min Act: -0.1700
Data Index: 751695 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.2278. Min Act: -0.1700
Data Index: 3676138 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.2278. Min Act: -0.1700
Data Index: 5122643 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.2278. Min Act: -0.1700
Data Index: 2630201 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.1965. Min Act: -0.1700
Data Index: 8202857 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.1965. Min Act: -0.1700
Data Index: 2431610 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.1965. Min Act: -0.1700
Data Index: 5302010 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.1965. Min Act: -0.1700
Data Index: 5581479 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.1965. Min Act: -0.1700
Data Index: 2654340 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.1965. Min Act: -0.1700
Data Index: 3098934 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.1965. Min Act: -0.1700
Data Index: 3516788 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5090. Min Range: -5.5090
Max Act: 5.2278. Min Act: -0.1700
Data Index: 5883150 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19