Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 586 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.5339. Min Act: -0.1693
Data Index: 843541 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4812. Min Act: -0.1700
Data Index: 6737616 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4812. Min Act: -0.1699
Data Index: 4789666 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4900. Min Act: -0.1699
Data Index: 6708058 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4725. Min Act: -0.1690
Data Index: 3777857 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4549. Min Act: -0.1700
Data Index: 7883046 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4461. Min Act: -0.1683
Data Index: 4295646 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4461. Min Act: -0.1700
Data Index: 349725 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4461. Min Act: -0.1699
Data Index: 8602630 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4461. Min Act: -0.1700
Data Index: 2403752 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4373. Min Act: -0.1700
Data Index: 5859657 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4461. Min Act: -0.1699
Data Index: 5862870 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4373. Min Act: -0.1698
Data Index: 3844469 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4285. Min Act: -0.1700
Data Index: 7516102 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4373. Min Act: -0.1700
Data Index: 4565748 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4373. Min Act: -0.1700
Data Index: 5037857 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4373. Min Act: -0.1700
Data Index: 5166443 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4461. Min Act: -0.1700
Data Index: 5335104 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4373. Min Act: -0.1694
Data Index: 3777859 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5339. Min Range: -1.5339
Max Act: 1.4373. Min Act: -0.1700
Data Index: 3269407 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19