Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0826. Min Range: -8.0826
Max Act: 8.0826. Min Act: -0.1700
Data Index: 6912869 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0826. Min Range: -8.0826
Max Act: 8.0201. Min Act: -0.1700
Data Index: 5475164 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0826. Min Range: -8.0826
Max Act: 8.0826. Min Act: -0.1700
Data Index: 1570844 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.9576. Min Act: -0.1700
Data Index: 5799206 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.9576. Min Act: -0.1700
Data Index: 2803726 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.9576. Min Act: -0.1700
Data Index: 242742 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.8639. Min Act: -0.1700
Data Index: 7166001 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.8951. Min Act: -0.1700
Data Index: 5236523 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.8326. Min Act: -0.1700
Data Index: 1205050 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.7701. Min Act: -0.1700
Data Index: 112803 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.7701. Min Act: -0.1700
Data Index: 4916770 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.8014. Min Act: -0.1700
Data Index: 5601728 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.7389. Min Act: -0.1700
Data Index: 2844603 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.7076. Min Act: -0.1700
Data Index: 996694 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.6451. Min Act: -0.1700
Data Index: 5335040 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.6764. Min Act: -0.1700
Data Index: 1106802 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.6451. Min Act: -0.1700
Data Index: 491349 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.6139. Min Act: -0.1700
Data Index: 7585858 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.6451. Min Act: -0.1700
Data Index: 6551469 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0826. Min Range: -8.0826
Max Act: 7.6139. Min Act: -0.1700
Data Index: 4427179 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19