Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1345 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1881. Min Act: -0.0005

Data Index: 459648 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1704. Min Act: -0.0005

Data Index: 911442 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1669. Min Act: -0.0005

Data Index: 441076 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1856. Min Act: -0.0005

Data Index: 1204466 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1807. Min Act: -0.0005

Data Index: 1066446 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1804. Min Act: -0.0005

Data Index: 273451 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1772. Min Act: -0.0005

Data Index: 501951 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1687. Min Act: -0.0005

Data Index: 299777 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1614. Min Act: -0.0005

Data Index: 998004 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1732. Min Act: -0.0005

Data Index: 1221693 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1623. Min Act: -0.0005

Data Index: 161778 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1602. Min Act: -0.0005

Data Index: 134876 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1708. Min Act: -0.0005

Data Index: 523575 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1773. Min Act: -0.0005

Data Index: 1204953 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1570. Min Act: -0.0005

Data Index: 888643 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1600. Min Act: -0.0005

Data Index: 1080979 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1590. Min Act: -0.0005

Data Index: 248487 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1642. Min Act: -0.0005

Data Index: 609073 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1537. Min Act: -0.0005

Data Index: 580719 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1511. Min Act: -0.0005

Data Index: 500870 (C4 (Web Text))

Max Activating Token Index: 288