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

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

Neuron 1909 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: 0.1369. Min Range: -0.1369

Max Act: 0.1369. Min Act: -0.0002

Data Index: 1577113 (Python Code)

Max Activating Token Index: 211

Text #1

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1300. Min Act: -0.0002

Data Index: 1635513 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1608393 (Python Code)

Max Activating Token Index: 833

Text #3

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1242. Min Act: -0.0002

Data Index: 1496012 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1372176 (Python Code)

Max Activating Token Index: 812

Text #5

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1600846 (Python Code)

Max Activating Token Index: 1022

Text #6

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1631415 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1176. Min Act: -0.0002

Data Index: 1390262 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1160. Min Act: -0.0002

Data Index: 1620061 (Python Code)

Max Activating Token Index: 935

Text #9

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1438292 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1507996 (Python Code)

Max Activating Token Index: 917

Text #11

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1450933 (Python Code)

Max Activating Token Index: 208

Text #12

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1410996 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1478339 (Python Code)

Max Activating Token Index: 754

Text #14

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1121. Min Act: -0.0002

Data Index: 1411905 (Python Code)

Max Activating Token Index: 470

Text #15

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1526106 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1622599 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1478786 (Python Code)

Max Activating Token Index: 644

Text #18

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1585413 (Python Code)

Max Activating Token Index: 711

Text #19

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1126. Min Act: -0.0002

Data Index: 1423636 (Python Code)

Max Activating Token Index: 510