Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 930 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0247. Min Act: -0.0004

Data Index: 833487 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0247. Min Act: -0.0003

Data Index: 148595 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0241. Min Act: -0.0004

Data Index: 887202 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1351213 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0224. Min Act: -0.0004

Data Index: 234039 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1179231 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1246737 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0208. Min Act: -0.0004

Data Index: 428843 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0207. Min Act: -0.0002

Data Index: 782795 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1121523 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0199. Min Act: -0.0003

Data Index: 550681 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0199. Min Act: -0.0004

Data Index: 298298 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0193. Min Act: -0.0003

Data Index: 343662 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0200. Min Act: -0.0003

Data Index: 8949 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0196. Min Act: -0.0003

Data Index: 345116 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0199. Min Act: -0.0004

Data Index: 288780 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0184. Min Act: -0.0004

Data Index: 494169 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1181404 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0193. Min Act: -0.0003

Data Index: 865364 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0180. Min Act: -0.0003

Data Index: 688632 (C4 (Web Text))

Max Activating Token Index: 854