Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1980 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1039085 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1082595 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1290. Min Act: -0.0000

Data Index: 725745 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1257. Min Act: -0.0000

Data Index: 347549 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1242. Min Act: -0.0000

Data Index: 289537 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1194. Min Act: -0.0000

Data Index: 86424 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1144. Min Act: -0.0000

Data Index: 735680 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1269. Min Act: -0.0000

Data Index: 153477 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1261. Min Act: -0.0000

Data Index: 507988 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1157. Min Act: -0.0000

Data Index: 868738 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1205. Min Act: -0.0000

Data Index: 815936 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1207. Min Act: -0.0000

Data Index: 464737 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1190. Min Act: -0.0000

Data Index: 686697 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1111. Min Act: -0.0000

Data Index: 381278 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1354221 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1123812 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1170. Min Act: -0.0000

Data Index: 939165 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1171. Min Act: -0.0000

Data Index: 731750 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1166. Min Act: -0.0000

Data Index: 161287 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1039596 (C4 (Web Text))

Max Activating Token Index: 221