Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2090 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1337732 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0332. Min Act: -0.0002

Data Index: 399697 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1048350 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0310. Min Act: -0.0002

Data Index: 390050 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0290. Min Act: -0.0002

Data Index: 792538 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0263. Min Act: -0.0002

Data Index: 582404 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0274. Min Act: -0.0002

Data Index: 902355 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0254. Min Act: -0.0002

Data Index: 54986 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1334137 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0263. Min Act: -0.0002

Data Index: 836663 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1210930 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0254. Min Act: -0.0002

Data Index: 227689 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1221144 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0272. Min Act: -0.0002

Data Index: 244801 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0270. Min Act: -0.0002

Data Index: 50243 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0265. Min Act: -0.0002

Data Index: 665488 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1055069 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0243. Min Act: -0.0002

Data Index: 827828 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0277. Min Act: -0.0002

Data Index: 131742 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0264. Min Act: -0.0002

Data Index: 685479 (C4 (Web Text))

Max Activating Token Index: 938