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

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

Neuron 778 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1312140 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1214400 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1010947 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0001

Data Index: 244937 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0262. Min Act: -0.0002

Data Index: 25827 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0234. Min Act: -0.0001

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1207657 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0224. Min Act: -0.0001

Data Index: 423414 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0217. Min Act: -0.0001

Data Index: 392450 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1314951 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0215. Min Act: -0.0001

Data Index: 824968 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1196208 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1214992 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0200. Min Act: -0.0002

Data Index: 215571 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1100688 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0192. Min Act: -0.0001

Data Index: 512788 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0192. Min Act: -0.0002

Data Index: 328838 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0186. Min Act: -0.0002

Data Index: 933689 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0187. Min Act: -0.0001

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1061368 (C4 (Web Text))

Max Activating Token Index: 698