Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5067 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2390. Min Range: -8.2390
Max Act: 8.2390. Min Act: -0.1700
Data Index: 3541274 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2390. Min Range: -8.2390
Max Act: 8.2390. Min Act: -0.1700
Data Index: 403027 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2390. Min Range: -8.2390
Max Act: 8.0827. Min Act: -0.1700
Data Index: 1429842 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2390. Min Range: -8.2390
Max Act: 8.0827. Min Act: -0.1700
Data Index: 7107481 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2390. Min Range: -8.2390
Max Act: 8.0202. Min Act: -0.1700
Data Index: 5548930 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2390. Min Range: -8.2390
Max Act: 8.0202. Min Act: -0.1700
Data Index: 3788642 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.9890. Min Act: -0.1700
Data Index: 5862930 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.8327. Min Act: -0.1700
Data Index: 2432698 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.7702. Min Act: -0.1700
Data Index: 7183796 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.7077. Min Act: -0.1700
Data Index: 8199921 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.7390. Min Act: -0.1700
Data Index: 1099437 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.7077. Min Act: -0.1700
Data Index: 4742139 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.7077. Min Act: -0.1700
Data Index: 15548 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.6765. Min Act: -0.1700
Data Index: 7299156 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.6765. Min Act: -0.1700
Data Index: 7074031 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.6765. Min Act: -0.1700
Data Index: 2590910 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.6452. Min Act: -0.1700
Data Index: 4635984 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.6452. Min Act: -0.1700
Data Index: 2244670 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.6452. Min Act: -0.1700
Data Index: 158638 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2390. Min Range: -8.2390
Max Act: 7.6140. Min Act: -0.1700
Data Index: 5334 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19