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

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

Neuron 1148 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0306. Min Act: -0.0006

Data Index: 1071247 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1358401 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1183831 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0212. Min Act: -0.0006

Data Index: 695235 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1068959 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1337644 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0225. Min Act: -0.0006

Data Index: 881103 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1211445 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0208. Min Act: -0.0006

Data Index: 141945 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1179319 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0207. Min Act: -0.0006

Data Index: 493441 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0212. Min Act: -0.0006

Data Index: 933872 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0211. Min Act: -0.0006

Data Index: 335913 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0218. Min Act: -0.0006

Data Index: 434335 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0194. Min Act: -0.0006

Data Index: 92438 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0207. Min Act: -0.0006

Data Index: 755180 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0197. Min Act: -0.0006

Data Index: 333569 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0198. Min Act: -0.0006

Data Index: 91345 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0196. Min Act: -0.0005

Data Index: 319533 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0187. Min Act: -0.0006

Data Index: 924267 (C4 (Web Text))

Max Activating Token Index: 446