Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 942 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0332. Min Range: -5.0332
Max Act: 5.0332. Min Act: -0.1700
Data Index: 1453738 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0332. Min Range: -5.0332
Max Act: 5.0019. Min Act: -0.1700
Data Index: 7330694 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0332. Min Range: -5.0332
Max Act: 5.0019. Min Act: -0.1700
Data Index: 6913431 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9082. Min Act: -0.1700
Data Index: 8427837 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9082. Min Act: -0.1700
Data Index: 8433037 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8457. Min Act: -0.1700
Data Index: 926822 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8769. Min Act: -0.1700
Data Index: 1208557 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8769. Min Act: -0.1700
Data Index: 8008432 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8769. Min Act: -0.1700
Data Index: 4018120 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8457. Min Act: -0.1700
Data Index: 7990340 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8457. Min Act: -0.1700
Data Index: 4418422 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8144. Min Act: -0.1700
Data Index: 1527331 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8144. Min Act: -0.1700
Data Index: 678096 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7832. Min Act: -0.1700
Data Index: 2083747 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7832. Min Act: -0.1700
Data Index: 6024789 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8144. Min Act: -0.1700
Data Index: 7492526 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8144. Min Act: -0.1700
Data Index: 6897760 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7832. Min Act: -0.1700
Data Index: 7022166 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7832. Min Act: -0.1700
Data Index: 200007 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8457. Min Act: -0.1700
Data Index: 1916497 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19