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

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

Neuron 3481 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: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0003

Data Index: 627217 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1231322 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1068282 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0287. Min Act: -0.0002

Data Index: 456159 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0280. Min Act: -0.0003

Data Index: 707038 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0280. Min Act: -0.0002

Data Index: 955120 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1128149 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0262. Min Act: -0.0002

Data Index: 337047 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0260. Min Act: -0.0003

Data Index: 928159 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0258. Min Act: -0.0003

Data Index: 677411 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0254. Min Act: -0.0003

Data Index: 825043 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0249. Min Act: -0.0003

Data Index: 317713 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1138917 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0248. Min Act: -0.0002

Data Index: 186823 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0246. Min Act: -0.0003

Data Index: 134398 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1133403 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0237. Min Act: -0.0002

Data Index: 406255 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1052286 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0238. Min Act: -0.0002

Data Index: 344847 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1055191 (C4 (Web Text))

Max Activating Token Index: 284