Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 982 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2665. Min Range: -8.2665
Max Act: 8.2665. Min Act: -0.1700
Data Index: 2512776 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2665. Min Range: -8.2665
Max Act: 8.2040. Min Act: -0.1700
Data Index: 8506289 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2665. Min Range: -8.2665
Max Act: 8.0790. Min Act: -0.1700
Data Index: 2107442 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.8915. Min Act: -0.1700
Data Index: 7680633 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.8290. Min Act: -0.1700
Data Index: 3900024 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.8290. Min Act: -0.1700
Data Index: 5522516 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.8290. Min Act: -0.1700
Data Index: 7667378 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.7665. Min Act: -0.1700
Data Index: 4753332 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.7665. Min Act: -0.1700
Data Index: 4702446 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.7665. Min Act: -0.1700
Data Index: 3278906 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.7665. Min Act: -0.1700
Data Index: 6836605 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.7040. Min Act: -0.1700
Data Index: 8472284 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.7040. Min Act: -0.1700
Data Index: 1779456 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.6727. Min Act: -0.1700
Data Index: 6680057 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.6727. Min Act: -0.1700
Data Index: 6799482 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.6102. Min Act: -0.1700
Data Index: 8390571 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.6102. Min Act: -0.1700
Data Index: 3599183 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.6102. Min Act: -0.1700
Data Index: 5316917 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.6102. Min Act: -0.1700
Data Index: 8600605 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2665. Min Range: -8.2665
Max Act: 7.6102. Min Act: -0.1700
Data Index: 2807129 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19