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

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

Neuron 2888 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: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0002

Data Index: 863890 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0250. Min Act: -0.0002

Data Index: 432633 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0228. Min Act: -0.0002

Data Index: 262522 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0231. Min Act: -0.0002

Data Index: 154664 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1067941 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1220687 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0217. Min Act: -0.0002

Data Index: 935035 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0206. Min Act: -0.0002

Data Index: 47520 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0184. Min Act: -0.0002

Data Index: 843013 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1576639 (Python Code)

Max Activating Token Index: 500

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0180. Min Act: -0.0002

Data Index: 639563 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0180. Min Act: -0.0002

Data Index: 694951 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1458401 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0176. Min Act: -0.0002

Data Index: 959780 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0199. Min Act: -0.0002

Data Index: 359360 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0189. Min Act: -0.0002

Data Index: 659007 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0191. Min Act: -0.0002

Data Index: 812069 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0190. Min Act: -0.0002

Data Index: 911840 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0174. Min Act: -0.0002

Data Index: 236005 (C4 (Web Text))

Max Activating Token Index: 540