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

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

Neuron 2097 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0886. Min Act: -0.0002

Data Index: 356597 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1467640 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1455670 (Python Code)

Max Activating Token Index: 221

Text #3

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1214255 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0633. Min Act: -0.0002

Data Index: 713261 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1501713 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0612. Min Act: -0.0002

Data Index: 324686 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1377934 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1036005 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0576. Min Act: -0.0002

Data Index: 873810 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1113770 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0605. Min Act: -0.0002

Data Index: 970502 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0639. Min Act: -0.0002

Data Index: 76806 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0612. Min Act: -0.0002

Data Index: 800693 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1288999 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0625. Min Act: -0.0002

Data Index: 687693 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1632265 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0611. Min Act: -0.0002

Data Index: 562549 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0623. Min Act: -0.0001

Data Index: 361249 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1232771 (C4 (Web Text))

Max Activating Token Index: 366