Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.8747. Min Act: -0.1700
Data Index: 4694680 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.6872. Min Act: -0.1700
Data Index: 8541904 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.3747. Min Act: -0.1700
Data Index: 3114336 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.4060. Min Act: -0.1700
Data Index: 2077358 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.4060. Min Act: -0.1700
Data Index: 1957433 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.3747. Min Act: -0.1700
Data Index: 7107862 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.3435. Min Act: -0.1700
Data Index: 8566574 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.2810. Min Act: -0.1700
Data Index: 709667 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.2497. Min Act: -0.1700
Data Index: 1545374 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.2497. Min Act: -0.1700
Data Index: 5305328 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.2185. Min Act: -0.1700
Data Index: 2214528 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.1872. Min Act: -0.1700
Data Index: 2803729 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.1560. Min Act: -0.1700
Data Index: 8364574 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.1560. Min Act: -0.1700
Data Index: 7940866 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.1872. Min Act: -0.1700
Data Index: 3524494 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.1560. Min Act: -0.1700
Data Index: 7187568 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.1247. Min Act: -0.1700
Data Index: 6700667 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.0935. Min Act: -0.1700
Data Index: 6756941 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.0935. Min Act: -0.1700
Data Index: 7316191 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8747. Min Range: -7.8747
Max Act: 7.0935. Min Act: -0.1700
Data Index: 2522883 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19