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

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

Neuron 1822 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0006

Data Index: 571494 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0784. Min Act: -0.0006

Data Index: 780391 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0690. Min Act: -0.0006

Data Index: 1014996 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0679. Min Act: -0.0006

Data Index: 719557 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0617. Min Act: -0.0006

Data Index: 915379 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0695. Min Act: -0.0006

Data Index: 38003 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0656. Min Act: -0.0006

Data Index: 883597 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0632. Min Act: -0.0006

Data Index: 305308 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0646. Min Act: -0.0006

Data Index: 688469 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0629. Min Act: -0.0006

Data Index: 291775 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0619. Min Act: -0.0006

Data Index: 1341012 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0656. Min Act: -0.0006

Data Index: 154782 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0627. Min Act: -0.0006

Data Index: 1264551 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0644. Min Act: -0.0006

Data Index: 1116365 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0630. Min Act: -0.0006

Data Index: 298202 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0656. Min Act: -0.0006

Data Index: 1034523 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0629. Min Act: -0.0006

Data Index: 1350956 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0625. Min Act: -0.0006

Data Index: 1296349 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0633. Min Act: -0.0006

Data Index: 943629 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0604. Min Act: -0.0006

Data Index: 909263 (C4 (Web Text))

Max Activating Token Index: 405