Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2459. Min Range: -9.2459
Max Act: 9.2459. Min Act: -0.1700
Data Index: 5108293 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2459. Min Range: -9.2459
Max Act: 9.1834. Min Act: -0.1700
Data Index: 2089225 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2459. Min Range: -9.2459
Max Act: 9.2459. Min Act: -0.1700
Data Index: 1615142 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2459. Min Range: -9.2459
Max Act: 9.1209. Min Act: -0.1700
Data Index: 5827242 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2459. Min Range: -9.2459
Max Act: 9.0584. Min Act: -0.1700
Data Index: 6732256 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.9959. Min Act: -0.1700
Data Index: 629398 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.9959. Min Act: -0.1700
Data Index: 5211909 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.9334. Min Act: -0.1700
Data Index: 5306754 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8709. Min Act: -0.1700
Data Index: 7811903 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8084. Min Act: -0.1700
Data Index: 3735858 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8709. Min Act: -0.1700
Data Index: 2109070 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8709. Min Act: -0.1700
Data Index: 350073 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8084. Min Act: -0.1700
Data Index: 4186005 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8084. Min Act: -0.1700
Data Index: 3158249 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8709. Min Act: -0.1700
Data Index: 3836500 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8084. Min Act: -0.1700
Data Index: 409591 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8084. Min Act: -0.1700
Data Index: 6824833 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8084. Min Act: -0.1700
Data Index: 1023396 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8084. Min Act: -0.1700
Data Index: 4942983 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2459. Min Range: -9.2459
Max Act: 8.8709. Min Act: -0.1700
Data Index: 6841851 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19