Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3781 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0386. Min Act: -0.0003

Data Index: 746058 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0315. Min Act: -0.0003

Data Index: 687342 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1269292 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0329. Min Act: -0.0003

Data Index: 89250 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0335. Min Act: -0.0003

Data Index: 157664 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0276. Min Act: -0.0003

Data Index: 721885 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0315. Min Act: -0.0003

Data Index: 175490 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1194282 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0300. Min Act: -0.0003

Data Index: 92192 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1100859 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0314. Min Act: -0.0004

Data Index: 52984 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0292. Min Act: -0.0003

Data Index: 18025 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1094901 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0292. Min Act: -0.0003

Data Index: 509174 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0225. Min Act: -0.0003

Data Index: 562849 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0314. Min Act: -0.0003

Data Index: 568845 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1291193 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1053796 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0281. Min Act: -0.0003

Data Index: 414630 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0245. Min Act: -0.0003

Data Index: 170854 (C4 (Web Text))

Max Activating Token Index: 185