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

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

Neuron 5312 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0275. Min Act: -0.0002

Data Index: 580358 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0247. Min Act: -0.0002

Data Index: 109764 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0243. Min Act: -0.0002

Data Index: 253583 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0237. Min Act: -0.0002

Data Index: 880312 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1033367 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0225. Min Act: -0.0002

Data Index: 792508 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0224. Min Act: -0.0002

Data Index: 852368 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0222. Min Act: -0.0002

Data Index: 271412 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1132690 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0215. Min Act: -0.0002

Data Index: 289886 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0216. Min Act: -0.0002

Data Index: 972185 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1220945 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0207. Min Act: -0.0002

Data Index: 366680 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0208. Min Act: -0.0002

Data Index: 766909 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0209. Min Act: -0.0002

Data Index: 791361 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0208. Min Act: -0.0003

Data Index: 996994 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1124541 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0205. Min Act: -0.0002

Data Index: 63336 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0201. Min Act: -0.0002

Data Index: 70937 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1184631 (C4 (Web Text))

Max Activating Token Index: 408