Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1081 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.7027. Min Act: -0.0001
Data Index: 157883 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.5103. Min Act: -0.0001
Data Index: 835856 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.4018. Min Act: -0.0001
Data Index: 406345 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.4610. Min Act: -0.0001
Data Index: 231435 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.3785. Min Act: -0.0001
Data Index: 956670 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.3006. Min Act: -0.0001
Data Index: 1071494 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.3405. Min Act: -0.0001
Data Index: 228989 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.3858. Min Act: -0.0001
Data Index: 1121373 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.3715. Min Act: -0.0001
Data Index: 928402 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.3868. Min Act: -0.0001
Data Index: 1166207 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.2243. Min Act: -0.0001
Data Index: 522837 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.1741. Min Act: -0.0001
Data Index: 1050419 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.2248. Min Act: -0.0001
Data Index: 1045160 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.2215. Min Act: -0.0001
Data Index: 561641 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.1678. Min Act: -0.0001
Data Index: 1230752 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.2966. Min Act: -0.0001
Data Index: 784787 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.2527. Min Act: -0.0001
Data Index: 1083226 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.2451. Min Act: -0.0001
Data Index: 1055206 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.1799. Min Act: -0.0001
Data Index: 1545910 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7027. Min Range: -1.7027
Max Act: 1.2168. Min Act: -0.0001
Data Index: 1560517 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19