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

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

Neuron 3653 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1261. Min Act: -0.0001

Data Index: 486921 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1247. Min Act: -0.0001

Data Index: 163916 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1193. Min Act: -0.0001

Data Index: 87142 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1066137 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1225. Min Act: -0.0001

Data Index: 807373 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1032794 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1296387 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1163. Min Act: -0.0001

Data Index: 816377 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1265026 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1095. Min Act: -0.0001

Data Index: 504665 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1065001 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1125. Min Act: -0.0001

Data Index: 570577 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1121. Min Act: -0.0001

Data Index: 53733 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1109. Min Act: -0.0001

Data Index: 352053 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1101. Min Act: -0.0001

Data Index: 861286 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1154. Min Act: -0.0001

Data Index: 12754 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1146311 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1146. Min Act: -0.0001

Data Index: 241462 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1000441 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1208842 (C4 (Web Text))

Max Activating Token Index: 218