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

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

Neuron 517 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: 0.0735. Min Range: -0.0735

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1625011 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0635. Min Act: -0.0003

Data Index: 901055 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0646. Min Act: -0.0003

Data Index: 860698 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0639. Min Act: -0.0004

Data Index: 215363 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0604. Min Act: -0.0003

Data Index: 746568 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0580. Min Act: -0.0004

Data Index: 1098006 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1612085 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1072109 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1497392 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1652356 (Python Code)

Max Activating Token Index: 783

Text #10

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0568. Min Act: -0.0002

Data Index: 944316 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0563. Min Act: -0.0003

Data Index: 477792 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1388091 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0543. Min Act: -0.0002

Data Index: 197527 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1656810 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0554. Min Act: -0.0003

Data Index: 558944 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0525. Min Act: -0.0003

Data Index: 401778 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1327673 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0537. Min Act: -0.0003

Data Index: 600798 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0536. Min Act: -0.0003

Data Index: 625360 (C4 (Web Text))

Max Activating Token Index: 203