Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.9122. Min Act: -0.1700
Data Index: 46114 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.7247. Min Act: -0.1700
Data Index: 4905376 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.6935. Min Act: -0.1700
Data Index: 4581450 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.6935. Min Act: -0.1700
Data Index: 1371074 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.6310. Min Act: -0.1700
Data Index: 2865935 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.6310. Min Act: -0.1700
Data Index: 2095769 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.6310. Min Act: -0.1700
Data Index: 4018756 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5997. Min Act: -0.1700
Data Index: 7475006 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5997. Min Act: -0.1700
Data Index: 6846674 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5372. Min Act: -0.1700
Data Index: 4148888 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5372. Min Act: -0.1700
Data Index: 7607275 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5685. Min Act: -0.1700
Data Index: 1659040 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5372. Min Act: -0.1700
Data Index: 4523564 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5372. Min Act: -0.1700
Data Index: 7015892 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5372. Min Act: -0.1700
Data Index: 7784236 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5372. Min Act: -0.1700
Data Index: 5718003 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.5060. Min Act: -0.1700
Data Index: 4683314 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.4747. Min Act: -0.1700
Data Index: 273308 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.4747. Min Act: -0.1700
Data Index: 996477 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9122. Min Range: -4.9122
Max Act: 4.4435. Min Act: -0.1700
Data Index: 701738 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19