Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3984 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.5625. Min Act: -0.1700
Data Index: 195822 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.5938. Min Act: -0.1700
Data Index: 898318 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.5938. Min Act: -0.1700
Data Index: 3517657 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.5000. Min Act: -0.1700
Data Index: 2013617 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.5313. Min Act: -0.1700
Data Index: 5921279 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.5313. Min Act: -0.1700
Data Index: 801721 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.5000. Min Act: -0.1700
Data Index: 5949759 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1133388 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4688. Min Act: -0.1700
Data Index: 5568541 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4688. Min Act: -0.1700
Data Index: 4295508 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1298170 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4688. Min Act: -0.1700
Data Index: 7265047 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4375. Min Act: -0.1700
Data Index: 2065888 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4062. Min Act: -0.1700
Data Index: 8433983 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4375. Min Act: -0.1700
Data Index: 4802976 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1160451 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4375. Min Act: -0.1700
Data Index: 2001780 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1024880 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4062. Min Act: -0.1700
Data Index: 6397649 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5938. Min Range: -4.5938
Max Act: 4.4062. Min Act: -0.1700
Data Index: 5232578 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19