Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0252. Min Range: -4.0252
Max Act: 4.0252. Min Act: -0.1700
Data Index: 4927355 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0252. Min Range: -4.0252
Max Act: 4.0252. Min Act: -0.1700
Data Index: 682626 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0252. Min Range: -4.0252
Max Act: 4.0096. Min Act: -0.1700
Data Index: 7977120 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.9939. Min Act: -0.1700
Data Index: 475005 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.9470. Min Act: -0.1700
Data Index: 2580198 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.9314. Min Act: -0.1700
Data Index: 8406926 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.9002. Min Act: -0.1700
Data Index: 3392848 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.9002. Min Act: -0.1700
Data Index: 4972048 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8845. Min Act: -0.1700
Data Index: 78280 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8845. Min Act: -0.1700
Data Index: 5632895 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8689. Min Act: -0.1700
Data Index: 6463770 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8532. Min Act: -0.1700
Data Index: 8167589 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8845. Min Act: -0.1700
Data Index: 7425654 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8689. Min Act: -0.1700
Data Index: 6340063 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8376. Min Act: -0.1700
Data Index: 5762620 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8689. Min Act: -0.1700
Data Index: 6474263 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8689. Min Act: -0.1700
Data Index: 2292527 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8845. Min Act: -0.1700
Data Index: 5174287 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8220. Min Act: -0.1700
Data Index: 5324066 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0252. Min Range: -4.0252
Max Act: 3.8689. Min Act: -0.1700
Data Index: 6798803 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19