Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 18 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2264. Min Act: -0.0000

Data Index: 238292 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1242696 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2005. Min Act: -0.0001

Data Index: 294435 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2012. Min Act: -0.0000

Data Index: 257160 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1889. Min Act: -0.0000

Data Index: 163538 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1324062 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1702. Min Act: -0.0001

Data Index: 855456 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1038758 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1856. Min Act: -0.0001

Data Index: 286839 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1128537 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1693. Min Act: -0.0001

Data Index: 803507 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1795. Min Act: -0.0001

Data Index: 674110 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1681. Min Act: -0.0000

Data Index: 863355 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1661. Min Act: -0.0000

Data Index: 507209 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1724. Min Act: -0.0000

Data Index: 307186 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1543. Min Act: -0.0000

Data Index: 303788 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1765. Min Act: -0.0001

Data Index: 198757 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1746. Min Act: -0.0001

Data Index: 134315 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1598. Min Act: -0.0000

Data Index: 118412 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1642. Min Act: -0.0001

Data Index: 544026 (C4 (Web Text))

Max Activating Token Index: 261