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

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

Neuron 2015 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3821. Min Act: -0.0000

Data Index: 659127 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3144. Min Act: -0.0000

Data Index: 123189 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2899. Min Act: -0.0000

Data Index: 292343 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2833. Min Act: -0.0000

Data Index: 456120 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2690. Min Act: -0.0000

Data Index: 43641 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2460. Min Act: -0.0000

Data Index: 203077 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2798. Min Act: -0.0000

Data Index: 18552 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2661. Min Act: -0.0000

Data Index: 283424 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2429. Min Act: -0.0000

Data Index: 973001 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2321. Min Act: -0.0000

Data Index: 223432 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2481. Min Act: -0.0000

Data Index: 884841 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2422. Min Act: -0.0000

Data Index: 293125 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2270. Min Act: -0.0000

Data Index: 459916 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2303. Min Act: -0.0000

Data Index: 806079 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2226. Min Act: -0.0000

Data Index: 846267 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2124. Min Act: -0.0000

Data Index: 378567 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2131. Min Act: -0.0000

Data Index: 612734 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2032. Min Act: -0.0000

Data Index: 365238 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1083511 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2164. Min Act: -0.0000

Data Index: 109610 (C4 (Web Text))

Max Activating Token Index: 666