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

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

Neuron 5293 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2743. Min Act: -0.0000

Data Index: 664430 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2806. Min Act: -0.0000

Data Index: 584535 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2849. Min Act: -0.0000

Data Index: 816385 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2856. Min Act: -0.0000

Data Index: 200432 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2517. Min Act: -0.0000

Data Index: 970343 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2684. Min Act: -0.0000

Data Index: 310230 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2304. Min Act: -0.0000

Data Index: 788707 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1220245 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2339. Min Act: -0.0000

Data Index: 745171 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2247. Min Act: -0.0000

Data Index: 696996 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2477. Min Act: -0.0000

Data Index: 354490 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2696. Min Act: -0.0000

Data Index: 433183 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1213764 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2278. Min Act: -0.0000

Data Index: 446438 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2391. Min Act: -0.0000

Data Index: 700885 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1138522 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2177. Min Act: -0.0000

Data Index: 271187 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2297. Min Act: -0.0000

Data Index: 221022 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2213. Min Act: -0.0000

Data Index: 254790 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2179. Min Act: -0.0000

Data Index: 600118 (C4 (Web Text))

Max Activating Token Index: 204