Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.9102. Min Act: -0.1700
Data Index: 1965772 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.8789. Min Act: -0.1700
Data Index: 4554461 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.8789. Min Act: -0.1700
Data Index: 7199652 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.8164. Min Act: -0.1700
Data Index: 4945656 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.8164. Min Act: -0.1700
Data Index: 5776001 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.7852. Min Act: -0.1700
Data Index: 3142023 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.7852. Min Act: -0.1700
Data Index: 7975264 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.7539. Min Act: -0.1700
Data Index: 5458915 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.7539. Min Act: -0.1700
Data Index: 1853304 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.7539. Min Act: -0.1700
Data Index: 4241493 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.7227. Min Act: -0.1700
Data Index: 5702004 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.6914. Min Act: -0.1700
Data Index: 7764047 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.6602. Min Act: -0.1700
Data Index: 2347787 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.6602. Min Act: -0.1700
Data Index: 39038 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.6602. Min Act: -0.1700
Data Index: 3766922 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.6289. Min Act: -0.1700
Data Index: 4755414 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.6602. Min Act: -0.1700
Data Index: 270327 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.6289. Min Act: -0.1700
Data Index: 8754466 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.6289. Min Act: -0.1700
Data Index: 7692063 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9102. Min Range: -4.9102
Max Act: 4.5977. Min Act: -0.1700
Data Index: 4576590 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19