Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5802 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.7789. Min Act: -0.1700
Data Index: 2672326 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.7164. Min Act: -0.1700
Data Index: 8378397 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.6226. Min Act: -0.1700
Data Index: 5837449 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.6539. Min Act: -0.1700
Data Index: 7807092 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.6539. Min Act: -0.1700
Data Index: 4164772 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.6539. Min Act: -0.1700
Data Index: 328606 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.6226. Min Act: -0.1700
Data Index: 7739066 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.6226. Min Act: -0.1700
Data Index: 3687432 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.6226. Min Act: -0.1700
Data Index: 3871809 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.6226. Min Act: -0.1700
Data Index: 3962683 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.5914. Min Act: -0.1700
Data Index: 6035822 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.6226. Min Act: -0.1700
Data Index: 7871852 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.5601. Min Act: -0.1700
Data Index: 3637249 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.5289. Min Act: -0.1700
Data Index: 8773710 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.5601. Min Act: -0.1700
Data Index: 8408687 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.5601. Min Act: -0.1700
Data Index: 5605635 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.5289. Min Act: -0.1700
Data Index: 6604582 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.5289. Min Act: -0.1700
Data Index: 6294708 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.4976. Min Act: -0.1700
Data Index: 431699 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7789. Min Range: -6.7789
Max Act: 6.4976. Min Act: -0.1700
Data Index: 4550594 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19