Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5331 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1854. Min Range: -7.1854
Max Act: 7.1854. Min Act: -0.1700
Data Index: 4387208 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1854. Min Range: -7.1854
Max Act: 7.1541. Min Act: -0.1700
Data Index: 728683 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1854. Min Range: -7.1854
Max Act: 7.1541. Min Act: -0.1700
Data Index: 6894787 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1854. Min Range: -7.1854
Max Act: 7.1229. Min Act: -0.1700
Data Index: 7821713 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1854. Min Range: -7.1854
Max Act: 7.0604. Min Act: -0.1700
Data Index: 285196 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.9666. Min Act: -0.1700
Data Index: 96202 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.9666. Min Act: -0.1700
Data Index: 2780550 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.9666. Min Act: -0.1700
Data Index: 6214825 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.9041. Min Act: -0.1700
Data Index: 2114991 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.8729. Min Act: -0.1700
Data Index: 6307688 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.8729. Min Act: -0.1700
Data Index: 8107358 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.8729. Min Act: -0.1700
Data Index: 1483990 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.8416. Min Act: -0.1700
Data Index: 5626905 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.8729. Min Act: -0.1700
Data Index: 5755021 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.8416. Min Act: -0.1700
Data Index: 6808915 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.8416. Min Act: -0.1700
Data Index: 5426822 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.8104. Min Act: -0.1700
Data Index: 6166146 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.8104. Min Act: -0.1700
Data Index: 1005527 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.7791. Min Act: -0.1700
Data Index: 4634006 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1854. Min Range: -7.1854
Max Act: 6.7791. Min Act: -0.1700
Data Index: 7766763 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19