Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.6853. Min Act: -0.1700
Data Index: 5268858 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.6853. Min Act: -0.1700
Data Index: 3474227 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.6228. Min Act: -0.1700
Data Index: 5507139 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.6540. Min Act: -0.1700
Data Index: 3958961 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.6228. Min Act: -0.1700
Data Index: 672794 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.5603. Min Act: -0.1700
Data Index: 3236149 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.5603. Min Act: -0.1700
Data Index: 1618752 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4978. Min Act: -0.1700
Data Index: 8157805 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4353. Min Act: -0.1700
Data Index: 6025797 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4665. Min Act: -0.1700
Data Index: 2538058 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4665. Min Act: -0.1700
Data Index: 6292421 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4665. Min Act: -0.1700
Data Index: 498866 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4353. Min Act: -0.1700
Data Index: 7181166 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4665. Min Act: -0.1700
Data Index: 7921456 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4665. Min Act: -0.1700
Data Index: 2547442 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4353. Min Act: -0.1700
Data Index: 361158 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4040. Min Act: -0.1700
Data Index: 2232947 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4353. Min Act: -0.1700
Data Index: 7762471 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4353. Min Act: -0.1700
Data Index: 1870616 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6853. Min Range: -4.6853
Max Act: 4.4353. Min Act: -0.1700
Data Index: 602078 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19