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

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

Neuron 427 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1073161 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1019686 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0192. Min Act: -0.0003

Data Index: 691248 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1194327 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0185. Min Act: -0.0003

Data Index: 501352 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0187. Min Act: -0.0003

Data Index: 84935 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0191. Min Act: -0.0002

Data Index: 659171 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1299631 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0180. Min Act: -0.0002

Data Index: 959486 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0179. Min Act: -0.0002

Data Index: 620127 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0172. Min Act: -0.0003

Data Index: 560025 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1248662 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1160318 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1323837 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0175. Min Act: -0.0003

Data Index: 716221 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0170. Min Act: -0.0002

Data Index: 659127 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0169. Min Act: -0.0003

Data Index: 654543 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1252764 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0160. Min Act: -0.0002

Data Index: 283008 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0162. Min Act: -0.0003

Data Index: 370826 (C4 (Web Text))

Max Activating Token Index: 829