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

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

Neuron 3454 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3555. Min Range: -1.3555

Max Act: 1.3555. Min Act: -0.0001

Data Index: 1196107 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.9428. Min Act: -0.0001

Data Index: 1280446 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.8556. Min Act: -0.0001

Data Index: 51202 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.8814. Min Act: -0.0001

Data Index: 917054 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7633. Min Act: -0.0001

Data Index: 206718 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7848. Min Act: -0.0001

Data Index: 788901 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7586. Min Act: -0.0001

Data Index: 820431 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7930. Min Act: -0.0001

Data Index: 655904 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7360. Min Act: -0.0001

Data Index: 540660 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7872. Min Act: -0.0001

Data Index: 1305388 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7338. Min Act: -0.0001

Data Index: 1334819 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.8500. Min Act: -0.0001

Data Index: 558817 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7790. Min Act: -0.0001

Data Index: 992509 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7198. Min Act: -0.0001

Data Index: 1167544 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7295. Min Act: -0.0001

Data Index: 1246698 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.6926. Min Act: -0.0001

Data Index: 1006983 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7056. Min Act: -0.0001

Data Index: 1578886 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.6793. Min Act: -0.0001

Data Index: 176611 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.6518. Min Act: -0.0001

Data Index: 625278 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.6719. Min Act: -0.0001

Data Index: 837808 (C4 (Web Text))

Max Activating Token Index: 576