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

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

Neuron 3094 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0003

Data Index: 482645 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0315. Min Act: -0.0003

Data Index: 582473 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0297. Min Act: -0.0003

Data Index: 371705 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0301. Min Act: -0.0003

Data Index: 526250 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0299. Min Act: -0.0003

Data Index: 712946 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1270193 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0288. Min Act: -0.0004

Data Index: 906449 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0269. Min Act: -0.0003

Data Index: 475889 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0287. Min Act: -0.0003

Data Index: 911418 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0284. Min Act: -0.0003

Data Index: 867997 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0288. Min Act: -0.0003

Data Index: 134747 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0265. Min Act: -0.0003

Data Index: 52970 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0273. Min Act: -0.0003

Data Index: 843510 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0271. Min Act: -0.0003

Data Index: 193090 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0272. Min Act: -0.0003

Data Index: 901482 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1020038 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0273. Min Act: -0.0003

Data Index: 868595 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1083290 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1275379 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0257. Min Act: -0.0003

Data Index: 342282 (C4 (Web Text))

Max Activating Token Index: 976