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

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

Neuron 4321 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: 0.1991. Min Range: -0.1991

Max Act: 0.1991. Min Act: -0.0002

Data Index: 1167881 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1835. Min Act: -0.0002

Data Index: 309770 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1701. Min Act: -0.0002

Data Index: 460032 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1745. Min Act: -0.0002

Data Index: 203375 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1793. Min Act: -0.0002

Data Index: 917175 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1711. Min Act: -0.0002

Data Index: 1318767 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1722. Min Act: -0.0002

Data Index: 1241990 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1710. Min Act: -0.0002

Data Index: 884527 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1768. Min Act: -0.0002

Data Index: 350767 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1676. Min Act: -0.0002

Data Index: 874960 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1727. Min Act: -0.0002

Data Index: 87524 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1608. Min Act: -0.0002

Data Index: 1077470 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1526. Min Act: -0.0002

Data Index: 1020760 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1550. Min Act: -0.0002

Data Index: 530095 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1543. Min Act: -0.0002

Data Index: 1112403 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1519. Min Act: -0.0002

Data Index: 1084062 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1460. Min Act: -0.0002

Data Index: 1246874 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1457. Min Act: -0.0002

Data Index: 875771 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1408. Min Act: -0.0002

Data Index: 1169683 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1420. Min Act: -0.0002

Data Index: 781278 (C4 (Web Text))

Max Activating Token Index: 702