Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2328 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.8751. Min Act: -0.1700
Data Index: 6734670 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.7969. Min Act: -0.1700
Data Index: 2711392 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.7813. Min Act: -0.1700
Data Index: 8534723 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.7656. Min Act: -0.1700
Data Index: 2000587 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.7813. Min Act: -0.1700
Data Index: 2772598 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.6718. Min Act: -0.1700
Data Index: 7378472 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.6874. Min Act: -0.1700
Data Index: 780817 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.6718. Min Act: -0.1700
Data Index: 6404049 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.6561. Min Act: -0.1700
Data Index: 5826680 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.6248. Min Act: -0.1700
Data Index: 8152427 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.6092. Min Act: -0.1700
Data Index: 7881788 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.6248. Min Act: -0.1700
Data Index: 6947195 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.5935. Min Act: -0.1700
Data Index: 5714200 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.5935. Min Act: -0.1700
Data Index: 4780955 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.5622. Min Act: -0.1700
Data Index: 8739584 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.5779. Min Act: -0.1700
Data Index: 3974693 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.5779. Min Act: -0.1700
Data Index: 4601219 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.5466. Min Act: -0.1700
Data Index: 4789691 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.5622. Min Act: -0.1700
Data Index: 7981462 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8751. Min Range: -3.8751
Max Act: 3.5779. Min Act: -0.1700
Data Index: 4477615 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19