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

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

Neuron 3517 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1489. Min Act: -0.0002

Data Index: 914601 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1518. Min Act: -0.0002

Data Index: 19330 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1277. Min Act: -0.0002

Data Index: 928703 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1253. Min Act: -0.0002

Data Index: 957055 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1266. Min Act: -0.0002

Data Index: 891209 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1245. Min Act: -0.0002

Data Index: 385527 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1271. Min Act: -0.0002

Data Index: 868756 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1179. Min Act: -0.0002

Data Index: 856208 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1210. Min Act: -0.0002

Data Index: 607090 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1198. Min Act: -0.0002

Data Index: 557126 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1171. Min Act: -0.0002

Data Index: 850395 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1194902 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1141. Min Act: -0.0002

Data Index: 465099 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1138. Min Act: -0.0002

Data Index: 178527 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1148. Min Act: -0.0002

Data Index: 16243 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1101. Min Act: -0.0002

Data Index: 1062566 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1043. Min Act: -0.0002

Data Index: 133090 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1078. Min Act: -0.0002

Data Index: 591456 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1213460 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1256517 (C4 (Web Text))

Max Activating Token Index: 331