Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 209 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1257. Min Act: -0.0003

Data Index: 134060 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1176. Min Act: -0.0003

Data Index: 549854 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1205. Min Act: -0.0003

Data Index: 654534 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1217. Min Act: -0.0003

Data Index: 1148929 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1200. Min Act: -0.0003

Data Index: 660186 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1048. Min Act: -0.0003

Data Index: 378704 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1123. Min Act: -0.0003

Data Index: 197169 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1174. Min Act: -0.0003

Data Index: 1029343 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1102. Min Act: -0.0003

Data Index: 221784 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1090. Min Act: -0.0003

Data Index: 1179734 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1108. Min Act: -0.0003

Data Index: 579709 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1090. Min Act: -0.0003

Data Index: 851538 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1113. Min Act: -0.0003

Data Index: 926468 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1159. Min Act: -0.0003

Data Index: 307577 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1120. Min Act: -0.0003

Data Index: 603289 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0983. Min Act: -0.0003

Data Index: 200620 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1148. Min Act: -0.0003

Data Index: 208489 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1086. Min Act: -0.0003

Data Index: 962771 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1053. Min Act: -0.0003

Data Index: 494349 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1040. Min Act: -0.0003

Data Index: 1071853 (C4 (Web Text))

Max Activating Token Index: 45