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

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

Neuron 5399 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: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0002

Data Index: 79616 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0315. Min Act: -0.0002

Data Index: 949062 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0305. Min Act: -0.0002

Data Index: 739114 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0306. Min Act: -0.0002

Data Index: 69931 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0285. Min Act: -0.0002

Data Index: 397597 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0292. Min Act: -0.0002

Data Index: 867314 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0284. Min Act: -0.0002

Data Index: 356033 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0274. Min Act: -0.0002

Data Index: 117159 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1046278 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0270. Min Act: -0.0002

Data Index: 737388 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0268. Min Act: -0.0002

Data Index: 167445 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0263. Min Act: -0.0002

Data Index: 684439 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0262. Min Act: -0.0002

Data Index: 641688 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0261. Min Act: -0.0002

Data Index: 148357 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0265. Min Act: -0.0002

Data Index: 828792 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0252. Min Act: -0.0002

Data Index: 166604 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0253. Min Act: -0.0002

Data Index: 709154 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0243. Min Act: -0.0002

Data Index: 929288 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0251. Min Act: -0.0002

Data Index: 334052 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0242. Min Act: -0.0002

Data Index: 576007 (C4 (Web Text))

Max Activating Token Index: 565