Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2780 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1822. Min Act: -0.0000

Data Index: 520424 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1136490 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1020895 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1634. Min Act: -0.0000

Data Index: 363345 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1633. Min Act: -0.0001

Data Index: 798222 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1597. Min Act: -0.0000

Data Index: 57847 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1307397 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1569. Min Act: -0.0000

Data Index: 797409 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1560. Min Act: -0.0000

Data Index: 14933 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1247991 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1564. Min Act: -0.0000

Data Index: 425504 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1533. Min Act: -0.0001

Data Index: 464968 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1452. Min Act: -0.0000

Data Index: 778370 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1498. Min Act: -0.0000

Data Index: 931468 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1298715 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1424. Min Act: -0.0001

Data Index: 575516 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1412. Min Act: -0.0000

Data Index: 288721 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1394. Min Act: -0.0000

Data Index: 849285 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1424. Min Act: -0.0001

Data Index: 806960 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1368. Min Act: -0.0001

Data Index: 917621 (C4 (Web Text))

Max Activating Token Index: 338