Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1797 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1454. Min Range: -7.1454
Max Act: 7.1454. Min Act: -0.1700
Data Index: 1551224 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1454. Min Range: -7.1454
Max Act: 7.0204. Min Act: -0.1700
Data Index: 924890 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1454. Min Range: -7.1454
Max Act: 7.0204. Min Act: -0.1700
Data Index: 6859236 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.9892. Min Act: -0.1700
Data Index: 2455275 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.9579. Min Act: -0.1700
Data Index: 5426627 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.9267. Min Act: -0.1700
Data Index: 2913151 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.9267. Min Act: -0.1700
Data Index: 2014518 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.9267. Min Act: -0.1700
Data Index: 6743918 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.9267. Min Act: -0.1700
Data Index: 2471212 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.9267. Min Act: -0.1700
Data Index: 5643481 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8954. Min Act: -0.1700
Data Index: 6894074 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8954. Min Act: -0.1700
Data Index: 7365082 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8642. Min Act: -0.1700
Data Index: 2458848 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8642. Min Act: -0.1700
Data Index: 2037454 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8329. Min Act: -0.1700
Data Index: 127357 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8329. Min Act: -0.1700
Data Index: 4594902 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8329. Min Act: -0.1700
Data Index: 8197813 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8329. Min Act: -0.1700
Data Index: 1900307 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8329. Min Act: -0.1700
Data Index: 6520978 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1454. Min Range: -7.1454
Max Act: 6.8329. Min Act: -0.1700
Data Index: 6460604 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19