Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2040 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0212. Min Act: -0.0006

Data Index: 995023 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0208. Min Act: -0.0006

Data Index: 456989 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0199. Min Act: -0.0006

Data Index: 593713 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0195. Min Act: -0.0006

Data Index: 697642 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0197. Min Act: -0.0006

Data Index: 886613 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0193. Min Act: -0.0006

Data Index: 427414 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1188312 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0189. Min Act: -0.0006

Data Index: 920766 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0188. Min Act: -0.0006

Data Index: 740362 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1194853 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0187. Min Act: -0.0006

Data Index: 459441 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1155736 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0186. Min Act: -0.0005

Data Index: 331436 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0181. Min Act: -0.0006

Data Index: 943372 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0184. Min Act: -0.0005

Data Index: 1050108 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0178. Min Act: -0.0006

Data Index: 300073 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1166302 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0181. Min Act: -0.0006

Data Index: 525110 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0180. Min Act: -0.0006

Data Index: 704157 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0179. Min Act: -0.0005

Data Index: 302876 (C4 (Web Text))

Max Activating Token Index: 851