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

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

Neuron 5423 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2604. Min Act: -0.0003

Data Index: 932056 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2606. Min Act: -0.0002

Data Index: 839476 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2260. Min Act: -0.0002

Data Index: 65830 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2315. Min Act: -0.0003

Data Index: 325673 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2236. Min Act: -0.0002

Data Index: 369258 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2269. Min Act: -0.0003

Data Index: 24590 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2248. Min Act: -0.0002

Data Index: 1244190 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2201. Min Act: -0.0003

Data Index: 632834 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2235. Min Act: -0.0002

Data Index: 126887 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2214. Min Act: -0.0003

Data Index: 673081 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2187. Min Act: -0.0002

Data Index: 393342 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2123. Min Act: -0.0002

Data Index: 1240173 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2165. Min Act: -0.0002

Data Index: 649587 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2118. Min Act: -0.0002

Data Index: 1005480 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2115. Min Act: -0.0002

Data Index: 1260956 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2117. Min Act: -0.0002

Data Index: 1050612 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2093. Min Act: -0.0002

Data Index: 355801 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2106. Min Act: -0.0002

Data Index: 293467 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2059. Min Act: -0.0003

Data Index: 49878 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.1997. Min Act: -0.0002

Data Index: 508186 (C4 (Web Text))

Max Activating Token Index: 1002