Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5827. Min Range: -7.5827
Max Act: 7.5827. Min Act: -0.1700
Data Index: 1333509 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5827. Min Range: -7.5827
Max Act: 7.2702. Min Act: -0.1700
Data Index: 6790990 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5827. Min Range: -7.5827
Max Act: 7.0202. Min Act: -0.1700
Data Index: 8023873 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5827. Min Range: -7.5827
Max Act: 7.0202. Min Act: -0.1700
Data Index: 1333508 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.9577. Min Act: -0.1700
Data Index: 6721843 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.9265. Min Act: -0.1700
Data Index: 7384772 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.8952. Min Act: -0.1700
Data Index: 8258845 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.8327. Min Act: -0.1700
Data Index: 486614 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.8327. Min Act: -0.1700
Data Index: 7036413 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.7390. Min Act: -0.1700
Data Index: 5396259 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.7077. Min Act: -0.1700
Data Index: 1276348 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.7390. Min Act: -0.1700
Data Index: 2187140 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.7390. Min Act: -0.1700
Data Index: 3025499 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.6765. Min Act: -0.1700
Data Index: 5794886 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.6452. Min Act: -0.1700
Data Index: 512744 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.6452. Min Act: -0.1700
Data Index: 1285738 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.6140. Min Act: -0.1700
Data Index: 8432809 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.5827. Min Act: -0.1700
Data Index: 374815 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.5827. Min Act: -0.1700
Data Index: 4220861 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5827. Min Range: -7.5827
Max Act: 6.5827. Min Act: -0.1700
Data Index: 3356861 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19