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

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

Neuron 2301 in Layer 1

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: 932010 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0282. Min Act: -0.0002

Data Index: 82627 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1096036 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0267. Min Act: -0.0002

Data Index: 621158 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0275. Min Act: -0.0003

Data Index: 594862 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0264. Min Act: -0.0002

Data Index: 949410 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0245. Min Act: -0.0002

Data Index: 889983 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0260. Min Act: -0.0002

Data Index: 321425 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0262. Min Act: -0.0002

Data Index: 433392 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1109746 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0254. Min Act: -0.0002

Data Index: 688411 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0235. Min Act: -0.0003

Data Index: 70711 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0247. Min Act: -0.0002

Data Index: 795639 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0239. Min Act: -0.0003

Data Index: 714607 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0226. Min Act: -0.0002

Data Index: 437959 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0224. Min Act: -0.0003

Data Index: 679864 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0214. Min Act: -0.0002

Data Index: 163160 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0226. Min Act: -0.0003

Data Index: 978942 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0221. Min Act: -0.0001

Data Index: 683836 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0216. Min Act: -0.0003

Data Index: 277454 (C4 (Web Text))

Max Activating Token Index: 198