Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5817 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.1829. Min Act: -0.1700
Data Index: 1741342 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.1517. Min Act: -0.1700
Data Index: 5901321 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.0892. Min Act: -0.1700
Data Index: 7823849 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.0579. Min Act: -0.1700
Data Index: 768114 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.0579. Min Act: -0.1700
Data Index: 7550809 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.0579. Min Act: -0.1700
Data Index: 3431789 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.0267. Min Act: -0.1700
Data Index: 696829 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.0267. Min Act: -0.1700
Data Index: 2959915 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.0267. Min Act: -0.1700
Data Index: 625096 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1829. Min Range: -6.1829
Max Act: 6.0267. Min Act: -0.1700
Data Index: 3502270 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9954. Min Act: -0.1700
Data Index: 8196690 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9954. Min Act: -0.1700
Data Index: 3694655 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9954. Min Act: -0.1700
Data Index: 7877017 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9954. Min Act: -0.1700
Data Index: 2029782 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9954. Min Act: -0.1700
Data Index: 1844899 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9642. Min Act: -0.1700
Data Index: 3779984 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9329. Min Act: -0.1700
Data Index: 4247477 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9329. Min Act: -0.1700
Data Index: 5235882 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9329. Min Act: -0.1700
Data Index: 5993335 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1829. Min Range: -6.1829
Max Act: 5.9329. Min Act: -0.1700
Data Index: 6981910 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19