Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 498 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.6558. Min Act: -0.1700
Data Index: 5844487 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.5932. Min Act: -0.1700
Data Index: 7717348 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.5306. Min Act: -0.1700
Data Index: 8228881 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4993. Min Act: -0.1700
Data Index: 8228885 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4993. Min Act: -0.1700
Data Index: 8228877 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4993. Min Act: -0.1700
Data Index: 4748056 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4679. Min Act: -0.1700
Data Index: 7717345 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4523. Min Act: -0.1700
Data Index: 5131400 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4523. Min Act: -0.1700
Data Index: 8228895 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4523. Min Act: -0.1700
Data Index: 8228886 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4366. Min Act: -0.1700
Data Index: 1604049 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4209. Min Act: -0.1700
Data Index: 7869707 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4366. Min Act: -0.1700
Data Index: 4461641 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4366. Min Act: -0.1700
Data Index: 6243121 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4366. Min Act: -0.1700
Data Index: 2001152 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4366. Min Act: -0.1700
Data Index: 5825680 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4366. Min Act: -0.1700
Data Index: 8228888 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4366. Min Act: -0.1700
Data Index: 3732607 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4366. Min Act: -0.1700
Data Index: 769331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6558. Min Range: -3.6558
Max Act: 3.4366. Min Act: -0.1700
Data Index: 7717329 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19