Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 730 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0784. Min Act: -0.0003

Data Index: 348433 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0003

Data Index: 435446 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0774. Min Act: -0.0003

Data Index: 818639 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0742. Min Act: -0.0003

Data Index: 678799 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0756. Min Act: -0.0003

Data Index: 753383 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1033879 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0767. Min Act: -0.0003

Data Index: 690792 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0734. Min Act: -0.0003

Data Index: 690901 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0735. Min Act: -0.0002

Data Index: 466957 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0727. Min Act: -0.0003

Data Index: 914674 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0716. Min Act: -0.0003

Data Index: 451331 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0714. Min Act: -0.0003

Data Index: 649645 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0698. Min Act: -0.0003

Data Index: 986406 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0701. Min Act: -0.0003

Data Index: 369379 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0704. Min Act: -0.0003

Data Index: 595217 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0707. Min Act: -0.0004

Data Index: 571231 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1308339 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0672. Min Act: -0.0003

Data Index: 213432 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0690. Min Act: -0.0003

Data Index: 792834 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0678. Min Act: -0.0003

Data Index: 870664 (C4 (Web Text))

Max Activating Token Index: 241