Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5028 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.9556. Min Act: -0.1700
Data Index: 4316308 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.9556. Min Act: -0.1700
Data Index: 5409903 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8931. Min Act: -0.1700
Data Index: 3629621 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8931. Min Act: -0.1700
Data Index: 4023399 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 4765820 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1699
Data Index: 2325826 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1699
Data Index: 2325807 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 277851 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 1970403 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 5399125 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 200889 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 4788747 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 884625 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 351047 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 523006 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 1674959 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 4343010 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 1153586 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.7681. Min Act: -0.1700
Data Index: 3567911 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9556. Min Range: -6.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 2591810 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19