Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 762 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0256. Min Act: -0.0004

Data Index: 360483 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0267. Min Act: -0.0004

Data Index: 494349 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0261. Min Act: -0.0004

Data Index: 460507 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0260. Min Act: -0.0004

Data Index: 255778 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0254. Min Act: -0.0004

Data Index: 109232 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0232. Min Act: -0.0004

Data Index: 887824 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0254. Min Act: -0.0004

Data Index: 1030691 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0235. Min Act: -0.0004

Data Index: 365380 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0253. Min Act: -0.0004

Data Index: 304911 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0242. Min Act: -0.0004

Data Index: 82690 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0004

Data Index: 1042025 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0235. Min Act: -0.0004

Data Index: 714905 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0203. Min Act: -0.0004

Data Index: 167065 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0212. Min Act: -0.0004

Data Index: 571574 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0246. Min Act: -0.0004

Data Index: 1290898 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0238. Min Act: -0.0004

Data Index: 998773 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0234. Min Act: -0.0004

Data Index: 767016 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0242. Min Act: -0.0004

Data Index: 214424 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0244. Min Act: -0.0004

Data Index: 216614 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0240. Min Act: -0.0004

Data Index: 620385 (C4 (Web Text))

Max Activating Token Index: 61