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

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

Neuron 65 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1346705 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1638562 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0686. Min Act: -0.0002

Data Index: 627611 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0666. Min Act: -0.0001

Data Index: 275802 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0666. Min Act: -0.0002

Data Index: 817317 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0635. Min Act: -0.0001

Data Index: 428985 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0665. Min Act: -0.0002

Data Index: 259495 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1235198 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1168950 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0654. Min Act: -0.0002

Data Index: 303311 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1178706 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0650. Min Act: -0.0002

Data Index: 514328 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0646. Min Act: -0.0002

Data Index: 246496 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1258880 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0635. Min Act: 0.0005

Data Index: 1301527 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0674. Min Act: -0.0002

Data Index: 886643 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1071368 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0627. Min Act: -0.0002

Data Index: 831650 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1108085 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0631. Min Act: 0.0012

Data Index: 1160716 (C4 (Web Text))

Max Activating Token Index: 54