Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 80 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.8720. Min Act: -0.1700
Data Index: 3103049 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.8243. Min Act: -0.1700
Data Index: 6985363 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.8084. Min Act: -0.1700
Data Index: 1726899 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.8084. Min Act: -0.1700
Data Index: 5465740 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.8084. Min Act: -0.1700
Data Index: 261161 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.8084. Min Act: -0.1700
Data Index: 6194995 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7925. Min Act: -0.1700
Data Index: 2301294 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7766. Min Act: -0.1700
Data Index: 7491934 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7766. Min Act: -0.1700
Data Index: 2212208 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7606. Min Act: -0.1700
Data Index: 6882224 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7606. Min Act: -0.1700
Data Index: 369878 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7606. Min Act: -0.1700
Data Index: 8270878 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7606. Min Act: -0.1700
Data Index: 7193060 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7606. Min Act: -0.1700
Data Index: 1892662 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7447. Min Act: -0.1700
Data Index: 8219840 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7606. Min Act: -0.1700
Data Index: 4033488 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7447. Min Act: -0.1700
Data Index: 1745365 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7606. Min Act: -0.1700
Data Index: 1264358 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7606. Min Act: -0.1700
Data Index: 239162 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8720. Min Range: -2.8720
Max Act: 2.7447. Min Act: -0.1700
Data Index: 4761759 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19