Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.5638. Min Act: -0.1700
Data Index: 7685391 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.4076. Min Act: -0.1700
Data Index: 1427698 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.3763. Min Act: -0.1700
Data Index: 2436614 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.3451. Min Act: -0.1700
Data Index: 7553755 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.3451. Min Act: -0.1700
Data Index: 6031785 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2513. Min Act: -0.1700
Data Index: 8310190 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2826. Min Act: -0.1700
Data Index: 3667204 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2513. Min Act: -0.1700
Data Index: 7146649 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1888. Min Act: -0.1700
Data Index: 6031788 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 5021276 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2513. Min Act: -0.1700
Data Index: 2655427 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1576. Min Act: -0.1700
Data Index: 5391654 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1576. Min Act: -0.1700
Data Index: 5706471 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1888. Min Act: -0.1700
Data Index: 3253988 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 6902340 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1888. Min Act: -0.1700
Data Index: 6503366 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1888. Min Act: -0.1700
Data Index: 6031795 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1888. Min Act: -0.1700
Data Index: 3265683 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1888. Min Act: -0.1700
Data Index: 6031782 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1576. Min Act: -0.1700
Data Index: 5114493 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19