Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.7247. Min Act: -0.1700
Data Index: 1843470 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.5997. Min Act: -0.1700
Data Index: 2847851 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.4747. Min Act: -0.1700
Data Index: 3458873 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.3497. Min Act: -0.1700
Data Index: 2154825 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.3497. Min Act: -0.1700
Data Index: 1117968 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.1622. Min Act: -0.1700
Data Index: 2519769 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.1622. Min Act: -0.1700
Data Index: 220191 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.0997. Min Act: -0.1700
Data Index: 2519768 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.1622. Min Act: -0.1700
Data Index: 2587843 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.0372. Min Act: -0.1700
Data Index: 7582923 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7247. Min Range: -8.7247
Max Act: 8.0997. Min Act: -0.1700
Data Index: 1946908 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7247. Min Range: -8.7247
Max Act: 7.9434. Min Act: -0.1700
Data Index: 3757596 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7247. Min Range: -8.7247
Max Act: 7.8497. Min Act: -0.1700
Data Index: 1855722 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7247. Min Range: -8.7247
Max Act: 7.8497. Min Act: -0.1700
Data Index: 2871425 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7247. Min Range: -8.7247
Max Act: 7.7872. Min Act: -0.1700
Data Index: 6988713 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7247. Min Range: -8.7247
Max Act: 7.7872. Min Act: -0.1700
Data Index: 1705189 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7247. Min Range: -8.7247
Max Act: 7.7872. Min Act: -0.1700
Data Index: 1808202 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7247. Min Range: -8.7247
Max Act: 7.7559. Min Act: -0.1700
Data Index: 2245064 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7247. Min Range: -8.7247
Max Act: 7.7559. Min Act: -0.1700
Data Index: 3867001 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7247. Min Range: -8.7247
Max Act: 7.7247. Min Act: -0.1700
Data Index: 5994189 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19