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

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

Neuron 2023 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0453. Min Act: -0.0002

Data Index: 702650 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0364. Min Act: -0.0002

Data Index: 91142 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0310. Min Act: -0.0002

Data Index: 289489 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0310. Min Act: -0.0002

Data Index: 989397 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0349. Min Act: -0.0002

Data Index: 306367 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1118679 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0277. Min Act: -0.0002

Data Index: 810626 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0270. Min Act: -0.0002

Data Index: 161408 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0268. Min Act: -0.0002

Data Index: 590821 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1036459 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0257. Min Act: -0.0002

Data Index: 596610 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0253. Min Act: -0.0002

Data Index: 192948 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1416 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0274. Min Act: -0.0002

Data Index: 4447 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1143401 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0250. Min Act: -0.0002

Data Index: 814033 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0227. Min Act: -0.0002

Data Index: 628543 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0247. Min Act: -0.0002

Data Index: 658729 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0216. Min Act: -0.0002

Data Index: 828146 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1336935 (C4 (Web Text))

Max Activating Token Index: 354