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

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

Neuron 4334 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.9745. Min Act: -0.0002

Data Index: 2104 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 5.4623. Min Range: -5.4623

Max Act: 5.4623. Min Act: -0.0002

Data Index: 733232 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.8626. Min Act: -0.0002

Data Index: 936494 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.8612. Min Act: -0.0002

Data Index: 377357 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.7955. Min Act: -0.0002

Data Index: 565616 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.9944. Min Act: -0.0002

Data Index: 920504 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.7912. Min Act: -0.0002

Data Index: 293178 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.9359. Min Act: -0.0002

Data Index: 1301056 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.7638. Min Act: -0.0002

Data Index: 196841 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.7070. Min Act: -0.0002

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.7273. Min Act: -0.0002

Data Index: 1045390 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.6859. Min Act: -0.0002

Data Index: 177476 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.4451. Min Act: -0.0002

Data Index: 601626 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.6117. Min Act: -0.0002

Data Index: 1300752 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.4704. Min Act: -0.0002

Data Index: 275675 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.7614. Min Act: -0.0002

Data Index: 14487 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.2510. Min Act: -0.0002

Data Index: 359339 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.4168. Min Act: -0.0002

Data Index: 938986 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.5556. Min Act: -0.0002

Data Index: 258081 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 5.4623. Min Range: -5.4623

Max Act: 4.5184. Min Act: -0.0002

Data Index: 552351 (C4 (Web Text))

Max Activating Token Index: 980