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

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

Neuron 2687 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1446327 (Python Code)

Max Activating Token Index: 370

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0298. Min Act: -0.0002

Data Index: 197654 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1373169 (Python Code)

Max Activating Token Index: 226

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1391042 (Python Code)

Max Activating Token Index: 154

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1562086 (Python Code)

Max Activating Token Index: 34

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0271. Min Act: -0.0002

Data Index: 617706 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0274. Min Act: -0.0002

Data Index: 226559 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0246. Min Act: -0.0002

Data Index: 799620 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1169319 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1343759 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1430714 (Python Code)

Max Activating Token Index: 177

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1127616 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0221. Min Act: -0.0002

Data Index: 576866 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0196. Min Act: -0.0002

Data Index: 325612 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0214. Min Act: -0.0002

Data Index: 267645 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0221. Min Act: -0.0002

Data Index: 459507 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0213. Min Act: -0.0002

Data Index: 106685 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0203. Min Act: -0.0002

Data Index: 951528 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1415796 (Python Code)

Max Activating Token Index: 481

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0203. Min Act: -0.0002

Data Index: 247367 (C4 (Web Text))

Max Activating Token Index: 313