Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4191 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1399. Min Act: -0.0002

Data Index: 561876 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1320. Min Act: -0.0002

Data Index: 129488 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1353. Min Act: -0.0002

Data Index: 937002 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1292. Min Act: -0.0002

Data Index: 877075 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1233. Min Act: -0.0002

Data Index: 5794 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1263. Min Act: -0.0002

Data Index: 434217 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1246. Min Act: -0.0002

Data Index: 965627 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1227. Min Act: -0.0002

Data Index: 285809 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1169. Min Act: -0.0002

Data Index: 273594 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1205. Min Act: -0.0002

Data Index: 638220 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1061847 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1182. Min Act: -0.0002

Data Index: 702993 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1160. Min Act: -0.0002

Data Index: 1020059 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1141. Min Act: -0.0002

Data Index: 974125 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1139. Min Act: -0.0002

Data Index: 737277 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1134. Min Act: -0.0002

Data Index: 432446 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1161. Min Act: -0.0002

Data Index: 245702 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1093. Min Act: -0.0002

Data Index: 7497 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1061. Min Act: -0.0002

Data Index: 800290 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1328660 (C4 (Web Text))

Max Activating Token Index: 438