Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2058 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.9187. Min Act: -0.1700
Data Index: 4523753 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.8249. Min Act: -0.1700
Data Index: 62006 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.7937. Min Act: -0.1700
Data Index: 6938936 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.7624. Min Act: -0.1700
Data Index: 1921593 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.6374. Min Act: -0.1700
Data Index: 4878532 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.6374. Min Act: -0.1700
Data Index: 6968014 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.6687. Min Act: -0.1700
Data Index: 5173014 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.6687. Min Act: -0.1700
Data Index: 6781788 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.5437. Min Act: -0.1700
Data Index: 1630012 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.5437. Min Act: -0.1700
Data Index: 8668905 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.5124. Min Act: -0.1700
Data Index: 8380079 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.5124. Min Act: -0.1700
Data Index: 2396976 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.5124. Min Act: -0.1700
Data Index: 6134468 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.4812. Min Act: -0.1700
Data Index: 6781772 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.4812. Min Act: -0.1700
Data Index: 682646 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.4812. Min Act: -0.1700
Data Index: 6032715 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.4812. Min Act: -0.1700
Data Index: 8627813 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.4812. Min Act: -0.1700
Data Index: 478241 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.5124. Min Act: -0.1700
Data Index: 5011608 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9187. Min Range: -4.9187
Max Act: 4.4812. Min Act: -0.1700
Data Index: 8014478 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19