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

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

Neuron 2923 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: 0.0222. Min Range: -0.0222

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1514604 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0002

Data Index: 13416 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1441076 (Python Code)

Max Activating Token Index: 965

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1584726 (Python Code)

Max Activating Token Index: 989

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1477608 (Python Code)

Max Activating Token Index: 328

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1125344 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1544105 (Python Code)

Max Activating Token Index: 326

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0156. Min Act: -0.0002

Data Index: 485891 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0141. Min Act: -0.0002

Data Index: 189575 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0145. Min Act: -0.0002

Data Index: 552677 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0134. Min Act: -0.0002

Data Index: 704074 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1643145 (Python Code)

Max Activating Token Index: 127

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1003713 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0129. Min Act: -0.0002

Data Index: 212962 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0136. Min Act: -0.0002

Data Index: 562667 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0146. Min Act: -0.0002

Data Index: 155352 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0142. Min Act: -0.0002

Data Index: 843642 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0154. Min Act: -0.0002

Data Index: 629733 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1392342 (Python Code)

Max Activating Token Index: 255

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1521632 (Python Code)

Max Activating Token Index: 506