Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3789. Min Range: -8.3789
Max Act: 8.3789. Min Act: -0.1700
Data Index: 8772377 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3789. Min Range: -8.3789
Max Act: 8.0039. Min Act: -0.1700
Data Index: 4992745 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.9727. Min Act: -0.1700
Data Index: 8680319 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.8789. Min Act: -0.1700
Data Index: 4992747 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.7227. Min Act: -0.1700
Data Index: 7137435 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.6914. Min Act: -0.1700
Data Index: 704733 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.6289. Min Act: -0.1700
Data Index: 1616595 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.5977. Min Act: -0.1700
Data Index: 5350000 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.5039. Min Act: -0.1700
Data Index: 905959 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.4414. Min Act: -0.1700
Data Index: 483262 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.4102. Min Act: -0.1700
Data Index: 8384697 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.3789. Min Act: -0.1700
Data Index: 2846034 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.3789. Min Act: -0.1700
Data Index: 3038036 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.3789. Min Act: -0.1700
Data Index: 1586867 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.3477. Min Act: -0.1700
Data Index: 5730344 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.3477. Min Act: -0.1700
Data Index: 2040433 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.3164. Min Act: -0.1700
Data Index: 8136448 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.2852. Min Act: -0.1700
Data Index: 2410999 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.2539. Min Act: -0.1700
Data Index: 7438060 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3789. Min Range: -8.3789
Max Act: 7.2227. Min Act: -0.1700
Data Index: 8136446 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19