Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1155 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0002

Data Index: 914899 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1247995 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0359. Min Act: -0.0002

Data Index: 46606 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1335027 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0380. Min Act: -0.0002

Data Index: 463569 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1469814 (Python Code)

Max Activating Token Index: 673

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1119413 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0352. Min Act: -0.0002

Data Index: 848575 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1129543 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0330. Min Act: -0.0002

Data Index: 995810 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0303. Min Act: -0.0002

Data Index: 11049 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0329. Min Act: -0.0002

Data Index: 36072 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0331. Min Act: -0.0002

Data Index: 21447 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0288. Min Act: -0.0002

Data Index: 970149 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1059535 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1134993 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0292. Min Act: -0.0002

Data Index: 598432 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0299. Min Act: -0.0002

Data Index: 66421 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0316. Min Act: -0.0002

Data Index: 71296 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0298. Min Act: -0.0002

Data Index: 965900 (C4 (Web Text))

Max Activating Token Index: 398