Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2991 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.6710. Min Act: -0.0000

Data Index: 1072461 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.6190. Min Act: -0.0000

Data Index: 1211701 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.4999. Min Act: -0.0000

Data Index: 102977 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.6996. Min Act: -0.0000

Data Index: 532835 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.5155. Min Act: -0.0000

Data Index: 1211256 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.5035. Min Act: -0.0000

Data Index: 331278 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.4295. Min Act: -0.0000

Data Index: 172749 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.5781. Min Act: -0.0000

Data Index: 1072171 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.5077. Min Act: -0.0000

Data Index: 565113 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.4788. Min Act: -0.0000

Data Index: 109373 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.3805. Min Act: -0.0000

Data Index: 70068 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.3798. Min Act: -0.0000

Data Index: 810378 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.4581. Min Act: -0.0000

Data Index: 462828 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.4544. Min Act: -0.0000

Data Index: 603237 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.4566. Min Act: -0.0000

Data Index: 864417 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.5413. Min Act: -0.0000

Data Index: 93271 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.5228. Min Act: -0.0000

Data Index: 1008208 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.5102. Min Act: -0.0000

Data Index: 337298 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.4267. Min Act: -0.0000

Data Index: 560955 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 1.6996. Min Range: -1.6996

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1231635 (C4 (Web Text))

Max Activating Token Index: 469