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

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

Neuron 346 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0000

Data Index: 163291 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0264. Min Act: -0.0001

Data Index: 702427 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1065368 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0252. Min Act: -0.0001

Data Index: 851938 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0241. Min Act: -0.0001

Data Index: 863571 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0225. Min Act: -0.0001

Data Index: 675100 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0229. Min Act: -0.0000

Data Index: 515592 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0204. Min Act: -0.0000

Data Index: 27635 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0228. Min Act: -0.0000

Data Index: 89046 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1178886 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1046253 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0195. Min Act: -0.0001

Data Index: 137499 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0211. Min Act: -0.0001

Data Index: 621865 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0199. Min Act: -0.0000

Data Index: 841265 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0195. Min Act: -0.0001

Data Index: 892358 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1157444 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0216. Min Act: -0.0000

Data Index: 655534 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0194. Min Act: -0.0000

Data Index: 968937 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1110799 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0209. Min Act: -0.0001

Data Index: 472505 (C4 (Web Text))

Max Activating Token Index: 840