Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5645 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.8992. Min Act: -0.1700
Data Index: 5563792 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.8680. Min Act: -0.1700
Data Index: 6432751 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.7430. Min Act: -0.1700
Data Index: 7299959 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.7430. Min Act: -0.1700
Data Index: 5351766 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.7117. Min Act: -0.1700
Data Index: 7935846 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.6492. Min Act: -0.1700
Data Index: 2906583 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.6180. Min Act: -0.1700
Data Index: 8055057 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.6180. Min Act: -0.1700
Data Index: 80857 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.6180. Min Act: -0.1700
Data Index: 3008097 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.6180. Min Act: -0.1700
Data Index: 5910410 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.6492. Min Act: -0.1700
Data Index: 2902208 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.5867. Min Act: -0.1700
Data Index: 1624439 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.5867. Min Act: -0.1700
Data Index: 4646409 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.5867. Min Act: -0.1700
Data Index: 5153430 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.5867. Min Act: -0.1700
Data Index: 82258 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.5867. Min Act: -0.1700
Data Index: 155576 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.5867. Min Act: -0.1700
Data Index: 8032987 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.5867. Min Act: -0.1700
Data Index: 2412350 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.5867. Min Act: -0.1700
Data Index: 3329106 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8992. Min Range: -5.8992
Max Act: 5.5555. Min Act: -0.1700
Data Index: 6097884 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19