Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 525 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0005

Data Index: 1572030 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1581321 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0363. Min Act: -0.0005

Data Index: 1552182 (Python Code)

Max Activating Token Index: 358

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0346. Min Act: -0.0005

Data Index: 1551463 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0254. Min Act: -0.0005

Data Index: 862978 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0229. Min Act: -0.0005

Data Index: 1484550 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0221. Min Act: -0.0005

Data Index: 1162598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0219. Min Act: -0.0005

Data Index: 1362472 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0219. Min Act: -0.0005

Data Index: 1629060 (Python Code)

Max Activating Token Index: 971

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0222. Min Act: -0.0005

Data Index: 1423910 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0216. Min Act: -0.0005

Data Index: 1513228 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0215. Min Act: -0.0005

Data Index: 1387613 (Python Code)

Max Activating Token Index: 607

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0212. Min Act: -0.0005

Data Index: 1464889 (Python Code)

Max Activating Token Index: 695

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0210. Min Act: -0.0005

Data Index: 1508171 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0207. Min Act: -0.0005

Data Index: 1396065 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0212. Min Act: -0.0005

Data Index: 1396705 (Python Code)

Max Activating Token Index: 678

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0199. Min Act: -0.0005

Data Index: 1556836 (Python Code)

Max Activating Token Index: 651

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0200. Min Act: -0.0005

Data Index: 11043 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1513334 (Python Code)

Max Activating Token Index: 770

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0203. Min Act: -0.0005

Data Index: 1511048 (Python Code)

Max Activating Token Index: 451