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

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

Neuron 2578 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1776. Min Act: -0.0000

Data Index: 867825 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1212576 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1585. Min Act: -0.0001

Data Index: 460867 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1498. Min Act: -0.0000

Data Index: 199886 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1244. Min Act: -0.0001

Data Index: 275333 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1440. Min Act: -0.0000

Data Index: 42400 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1412. Min Act: -0.0001

Data Index: 391281 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1300. Min Act: -0.0000

Data Index: 819772 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1396. Min Act: -0.0001

Data Index: 767053 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1342. Min Act: -0.0000

Data Index: 348865 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1328. Min Act: -0.0000

Data Index: 423098 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1158. Min Act: -0.0000

Data Index: 894104 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1181. Min Act: -0.0000

Data Index: 692999 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1256. Min Act: -0.0000

Data Index: 468998 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1266. Min Act: -0.0000

Data Index: 750677 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1154688 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1252. Min Act: -0.0000

Data Index: 540923 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1014834 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1236. Min Act: -0.0001

Data Index: 391173 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1198. Min Act: -0.0000

Data Index: 882479 (C4 (Web Text))

Max Activating Token Index: 567