Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5447. Min Range: -12.5447
Max Act: 12.5447. Min Act: -0.1700
Data Index: 7839168 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5447. Min Range: -12.5447
Max Act: 10.4197. Min Act: -0.1700
Data Index: 3373786 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5447. Min Range: -12.5447
Max Act: 10.2322. Min Act: -0.1700
Data Index: 4490106 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5447. Min Range: -12.5447
Max Act: 10.1072. Min Act: -0.1700
Data Index: 4719964 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5447. Min Range: -12.5447
Max Act: 10.1072. Min Act: -0.1700
Data Index: 792435 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5447. Min Range: -12.5447
Max Act: 10.1072. Min Act: -0.1700
Data Index: 4279977 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5447. Min Range: -12.5447
Max Act: 10.0447. Min Act: -0.1700
Data Index: 1695290 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5447. Min Range: -12.5447
Max Act: 10.0447. Min Act: -0.1700
Data Index: 650301 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.9197. Min Act: -0.1700
Data Index: 952223 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.7947. Min Act: -0.1700
Data Index: 7447125 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.7947. Min Act: -0.1700
Data Index: 7023836 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.8572. Min Act: -0.1700
Data Index: 6721907 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.7947. Min Act: -0.1700
Data Index: 7964859 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.7947. Min Act: -0.1700
Data Index: 1969662 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.7322. Min Act: -0.1700
Data Index: 8705442 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.7322. Min Act: -0.1700
Data Index: 4480201 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.7322. Min Act: -0.1700
Data Index: 6721158 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.6072. Min Act: -0.1700
Data Index: 382094 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.6697. Min Act: -0.1700
Data Index: 7887127 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5447. Min Range: -12.5447
Max Act: 9.6697. Min Act: -0.1700
Data Index: 5044753 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19