Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2234 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.7446. Min Act: -0.1700
Data Index: 418323 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.6977. Min Act: -0.1700
Data Index: 3960657 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.6194. Min Act: -0.1700
Data Index: 2738887 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.6194. Min Act: -0.1700
Data Index: 7866749 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.5568. Min Act: -0.1700
Data Index: 1983865 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.5099. Min Act: -0.1700
Data Index: 2238622 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4942. Min Act: -0.1700
Data Index: 7438782 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4629. Min Act: -0.1700
Data Index: 6001017 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4629. Min Act: -0.1700
Data Index: 7190581 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4785. Min Act: -0.1700
Data Index: 2917605 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4315. Min Act: -0.1700
Data Index: 1273215 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4472. Min Act: -0.1700
Data Index: 4634865 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4629. Min Act: -0.1700
Data Index: 4834672 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4158. Min Act: -0.1700
Data Index: 2283162 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4158. Min Act: -0.1700
Data Index: 8761352 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.3845. Min Act: -0.1700
Data Index: 2589669 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4002. Min Act: -0.1700
Data Index: 2629979 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.3845. Min Act: -0.1700
Data Index: 3882484 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.3688. Min Act: -0.1700
Data Index: 5098595 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7446. Min Range: -3.7446
Max Act: 3.4002. Min Act: -0.1700
Data Index: 6177110 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19