Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1018 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1097142 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1301. Min Act: -0.0002

Data Index: 166031 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1298. Min Act: -0.0001

Data Index: 170410 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1265. Min Act: -0.0002

Data Index: 843124 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1244. Min Act: -0.0001

Data Index: 706202 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1029129 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1190. Min Act: -0.0001

Data Index: 831249 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1184. Min Act: -0.0002

Data Index: 1029479 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1222. Min Act: -0.0001

Data Index: 218777 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1120116 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1121. Min Act: -0.0001

Data Index: 431981 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1150. Min Act: -0.0001

Data Index: 661941 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1159. Min Act: -0.0001

Data Index: 22918 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1156. Min Act: -0.0002

Data Index: 799152 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1168679 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1311935 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1130. Min Act: -0.0001

Data Index: 811338 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1157. Min Act: -0.0001

Data Index: 43608 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1115. Min Act: -0.0001

Data Index: 987130 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1141. Min Act: -0.0002

Data Index: 719454 (C4 (Web Text))

Max Activating Token Index: 53