Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 775 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0856. Min Act: -0.0003

Data Index: 1516045 (Python Code)

Max Activating Token Index: 135

Text #1

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0772. Min Act: -0.0003

Data Index: 1497805 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1134433 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0674. Min Act: -0.0003

Data Index: 367841 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1571595 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1369174 (Python Code)

Max Activating Token Index: 612

Text #6

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0664. Min Act: -0.0003

Data Index: 442631 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1462947 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0622. Min Act: -0.0002

Data Index: 522665 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1469091 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1530322 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1333888 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1425494 (Python Code)

Max Activating Token Index: 733

Text #13

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1392696 (Python Code)

Max Activating Token Index: 723

Text #14

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1508423 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1640290 (Python Code)

Max Activating Token Index: 865

Text #16

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1483741 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0604. Min Act: -0.0003

Data Index: 324033 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0614. Min Act: -0.0003

Data Index: 856801 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1536433 (Python Code)

Max Activating Token Index: 422