Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1320 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1631982 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 776308 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0350. Min Act: -0.0002

Data Index: 549595 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1208979 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1087727 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1276637 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0329. Min Act: -0.0003

Data Index: 775374 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0327. Min Act: -0.0003

Data Index: 832508 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0313. Min Act: -0.0003

Data Index: 523274 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0286. Min Act: -0.0003

Data Index: 468733 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1073906 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0287. Min Act: -0.0002

Data Index: 107859 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1131274 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0286. Min Act: -0.0002

Data Index: 597358 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0290. Min Act: -0.0003

Data Index: 371020 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0283. Min Act: -0.0003

Data Index: 286942 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1240558 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0270. Min Act: -0.0002

Data Index: 133566 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0275. Min Act: -0.0002

Data Index: 923756 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0277. Min Act: -0.0002

Data Index: 715757 (C4 (Web Text))

Max Activating Token Index: 12