Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 656 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0004

Data Index: 732083 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0309. Min Act: -0.0003

Data Index: 591799 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0307. Min Act: -0.0003

Data Index: 777838 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0313. Min Act: -0.0003

Data Index: 507652 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0301. Min Act: -0.0003

Data Index: 606013 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0301. Min Act: -0.0003

Data Index: 537 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0302. Min Act: -0.0004

Data Index: 1112805 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0292. Min Act: -0.0004

Data Index: 982211 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0297. Min Act: -0.0004

Data Index: 657786 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0295. Min Act: -0.0004

Data Index: 40850 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0290. Min Act: -0.0003

Data Index: 728802 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0294. Min Act: -0.0003

Data Index: 599870 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0294. Min Act: -0.0003

Data Index: 604374 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0284. Min Act: -0.0004

Data Index: 776038 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0297. Min Act: -0.0003

Data Index: 111431 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0289. Min Act: -0.0003

Data Index: 939033 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0285. Min Act: -0.0003

Data Index: 228286 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1282383 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0287. Min Act: -0.0003

Data Index: 534378 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1029388 (C4 (Web Text))

Max Activating Token Index: 430