Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1576 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2298. Min Range: -8.2298
Max Act: 8.2298. Min Act: -0.1700
Data Index: 6806296 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2298. Min Range: -8.2298
Max Act: 8.1048. Min Act: -0.1700
Data Index: 852483 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.9173. Min Act: -0.1700
Data Index: 3265109 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.7923. Min Act: -0.1700
Data Index: 7281174 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.7923. Min Act: -0.1700
Data Index: 5049354 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.7923. Min Act: -0.1700
Data Index: 124123 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.6673. Min Act: -0.1700
Data Index: 2106048 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.7298. Min Act: -0.1700
Data Index: 628482 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.7923. Min Act: -0.1700
Data Index: 5819224 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.7298. Min Act: -0.1700
Data Index: 5910723 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.7298. Min Act: -0.1700
Data Index: 3285233 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.6673. Min Act: -0.1700
Data Index: 1392673 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.6673. Min Act: -0.1700
Data Index: 7353178 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.6673. Min Act: -0.1700
Data Index: 3802879 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.6673. Min Act: -0.1700
Data Index: 7769425 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.7298. Min Act: -0.1700
Data Index: 5980967 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.6673. Min Act: -0.1700
Data Index: 504333 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.6048. Min Act: -0.1700
Data Index: 566211 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.6048. Min Act: -0.1700
Data Index: 645602 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2298. Min Range: -8.2298
Max Act: 7.5423. Min Act: -0.1700
Data Index: 4052700 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19