Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4461 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0002

Data Index: 345783 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1264523 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0391. Min Act: -0.0002

Data Index: 566244 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0383. Min Act: -0.0002

Data Index: 142959 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0379. Min Act: -0.0002

Data Index: 22934 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0378. Min Act: -0.0002

Data Index: 733760 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0371. Min Act: -0.0002

Data Index: 613369 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0360. Min Act: -0.0002

Data Index: 81263 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0354. Min Act: -0.0002

Data Index: 707440 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1002345 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0367. Min Act: -0.0002

Data Index: 178674 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0359. Min Act: -0.0002

Data Index: 86837 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0356. Min Act: -0.0002

Data Index: 942430 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0355. Min Act: -0.0002

Data Index: 471553 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0348. Min Act: -0.0002

Data Index: 299999 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0347. Min Act: -0.0002

Data Index: 330868 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0343. Min Act: -0.0002

Data Index: 115069 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1247955 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0346. Min Act: -0.0002

Data Index: 669483 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0358. Min Act: -0.0002

Data Index: 544679 (C4 (Web Text))

Max Activating Token Index: 674