Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6032 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.2839. Min Act: -0.1700
Data Index: 7233614 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.1589. Min Act: -0.1700
Data Index: 1930285 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.1589. Min Act: -0.1700
Data Index: 3785128 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.1589. Min Act: -0.1700
Data Index: 1048495 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.1589. Min Act: -0.1700
Data Index: 4710947 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.1589. Min Act: -0.1700
Data Index: 8223129 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.1276. Min Act: -0.1700
Data Index: 8413642 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.1276. Min Act: -0.1700
Data Index: 6180879 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.0651. Min Act: -0.1700
Data Index: 5498409 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.0026. Min Act: -0.1700
Data Index: 1142447 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.0338. Min Act: -0.1700
Data Index: 7476910 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.0026. Min Act: -0.1700
Data Index: 1212045 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.0026. Min Act: -0.1700
Data Index: 7448920 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.0338. Min Act: -0.1700
Data Index: 3102002 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2839. Min Range: -4.2839
Max Act: 4.0026. Min Act: -0.1700
Data Index: 3980567 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2839. Min Range: -4.2839
Max Act: 3.9713. Min Act: -0.1700
Data Index: 738235 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2839. Min Range: -4.2839
Max Act: 3.9713. Min Act: -0.1700
Data Index: 4415946 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2839. Min Range: -4.2839
Max Act: 3.9401. Min Act: -0.1700
Data Index: 4947723 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2839. Min Range: -4.2839
Max Act: 3.9713. Min Act: -0.1700
Data Index: 2173250 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2839. Min Range: -4.2839
Max Act: 3.9713. Min Act: -0.1700
Data Index: 3102000 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19