Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5530 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.6120. Min Act: -0.1700
Data Index: 2995806 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.6120. Min Act: -0.1700
Data Index: 2767299 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.4557. Min Act: -0.1700
Data Index: 2494965 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.3307. Min Act: -0.1700
Data Index: 492810 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.3307. Min Act: -0.1700
Data Index: 8735678 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.2682. Min Act: -0.1700
Data Index: 3768778 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.2057. Min Act: -0.1700
Data Index: 1898678 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.2370. Min Act: -0.1700
Data Index: 2135601 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.2370. Min Act: -0.1700
Data Index: 2035545 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.2057. Min Act: -0.1700
Data Index: 7849714 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.2057. Min Act: -0.1700
Data Index: 4428466 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.1745. Min Act: -0.1700
Data Index: 2522693 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.1432. Min Act: -0.1700
Data Index: 3329837 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.1745. Min Act: -0.1700
Data Index: 131391 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.1432. Min Act: -0.1700
Data Index: 3035854 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.0807. Min Act: -0.1700
Data Index: 2951026 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.1120. Min Act: -0.1700
Data Index: 8425309 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.0807. Min Act: -0.1700
Data Index: 2752511 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.0807. Min Act: -0.1700
Data Index: 3022953 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6120. Min Range: -7.6120
Max Act: 7.0495. Min Act: -0.1700
Data Index: 7304176 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19