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

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

Neuron 1094 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1398. Min Act: -0.0003

Data Index: 804116 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1291. Min Act: -0.0002

Data Index: 814795 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1255. Min Act: -0.0002

Data Index: 646231 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1236. Min Act: -0.0002

Data Index: 180752 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1225. Min Act: -0.0002

Data Index: 791946 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1233. Min Act: -0.0002

Data Index: 426826 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1208. Min Act: -0.0002

Data Index: 485426 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1220. Min Act: -0.0002

Data Index: 609086 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1201. Min Act: -0.0002

Data Index: 769545 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1240423 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1183. Min Act: -0.0002

Data Index: 75942 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1170. Min Act: -0.0002

Data Index: 910723 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1178. Min Act: -0.0002

Data Index: 244645 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1159. Min Act: -0.0002

Data Index: 303236 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1152. Min Act: -0.0002

Data Index: 269228 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1186. Min Act: -0.0002

Data Index: 830269 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1152. Min Act: -0.0002

Data Index: 530452 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1155. Min Act: -0.0002

Data Index: 671903 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1340520 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1168. Min Act: -0.0002

Data Index: 1008586 (C4 (Web Text))

Max Activating Token Index: 73