Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4886. Min Range: -8.4886
Max Act: 8.4886. Min Act: -0.1700
Data Index: 6418796 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4886. Min Range: -8.4886
Max Act: 8.0511. Min Act: -0.1700
Data Index: 2764272 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.8636. Min Act: -0.1700
Data Index: 8166819 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.9261. Min Act: -0.1700
Data Index: 5956717 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.7699. Min Act: -0.1700
Data Index: 148374 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.5824. Min Act: -0.1700
Data Index: 1971584 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.4574. Min Act: -0.1700
Data Index: 4305287 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.4886. Min Act: -0.1700
Data Index: 6305899 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.4574. Min Act: -0.1700
Data Index: 5397737 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.5199. Min Act: -0.1700
Data Index: 4263178 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.3636. Min Act: -0.1700
Data Index: 8441414 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.3324. Min Act: -0.1700
Data Index: 1879017 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.2386. Min Act: -0.1700
Data Index: 7309694 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.3011. Min Act: -0.1700
Data Index: 8342890 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.2386. Min Act: -0.1700
Data Index: 4292166 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.2074. Min Act: -0.1700
Data Index: 3313134 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.2699. Min Act: -0.1700
Data Index: 5100790 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.3324. Min Act: -0.1700
Data Index: 6744972 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.1761. Min Act: -0.1700
Data Index: 3080097 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4886. Min Range: -8.4886
Max Act: 7.1449. Min Act: -0.1700
Data Index: 2067293 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19