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

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

Neuron 1406 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.1027. Min Act: -0.0001

Data Index: 195102 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1618598 (Python Code)

Max Activating Token Index: 618

Text #2

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1471472 (Python Code)

Max Activating Token Index: 417

Text #3

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1517736 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1522443 (Python Code)

Max Activating Token Index: 547

Text #5

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1141749 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1531382 (Python Code)

Max Activating Token Index: 916

Text #7

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0675. Min Act: -0.0001

Data Index: 770040 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0611. Min Act: -0.0001

Data Index: 512017 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0621. Min Act: -0.0001

Data Index: 1288557 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0619. Min Act: -0.0001

Data Index: 631982 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1008236 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0631. Min Act: -0.0001

Data Index: 910597 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0614. Min Act: -0.0001

Data Index: 34838 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0575. Min Act: -0.0001

Data Index: 659715 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0571. Min Act: -0.0001

Data Index: 347225 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0604. Min Act: -0.0001

Data Index: 866428 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1281872 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1618411 (Python Code)

Max Activating Token Index: 885

Text #19

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1513921 (Python Code)

Max Activating Token Index: 841