Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.9758. Min Act: -0.1015
Data Index: 7041693 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.9249. Min Act: -0.1700
Data Index: 1463138 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.8737. Min Act: -0.1106
Data Index: 6029665 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.8566. Min Act: -0.1695
Data Index: 1818962 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.8566. Min Act: -0.1662
Data Index: 1772823 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.8395. Min Act: -0.1454
Data Index: 7588592 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.8223. Min Act: -0.1433
Data Index: 8771439 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.8223. Min Act: -0.1165
Data Index: 2434513 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.8223. Min Act: -0.1665
Data Index: 7518986 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.8051. Min Act: -0.1696
Data Index: 2198152 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.8051. Min Act: -0.1700
Data Index: 8169142 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.7707. Min Act: -0.1626
Data Index: 291526 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.7707. Min Act: -0.1527
Data Index: 900880 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.7879. Min Act: -0.1688
Data Index: 6620476 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.7879. Min Act: -0.1660
Data Index: 6875552 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.7707. Min Act: -0.1700
Data Index: 4460831 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.7361. Min Act: -0.0930
Data Index: 8454856 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.7707. Min Act: -0.1610
Data Index: 5740709 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.7707. Min Act: -0.1684
Data Index: 5201318 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9758. Min Range: -1.9758
Max Act: 1.7707. Min Act: -0.0824
Data Index: 8771414 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19