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

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

Neuron 5233 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1185028 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0001

Data Index: 409650 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0281. Min Act: -0.0001

Data Index: 869038 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0243. Min Act: -0.0001

Data Index: 622553 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1329592 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0252. Min Act: -0.0002

Data Index: 379887 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0263. Min Act: -0.0001

Data Index: 337273 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0263. Min Act: -0.0001

Data Index: 246335 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1095450 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0238. Min Act: -0.0001

Data Index: 567604 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0251. Min Act: -0.0001

Data Index: 190247 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0254. Min Act: -0.0001

Data Index: 652394 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1127399 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0224. Min Act: -0.0001

Data Index: 652336 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0225. Min Act: -0.0001

Data Index: 649704 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0217. Min Act: -0.0001

Data Index: 339243 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0232. Min Act: -0.0001

Data Index: 283488 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1123338 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0227. Min Act: -0.0001

Data Index: 45458 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1117369 (C4 (Web Text))

Max Activating Token Index: 426