Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4650 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0002

Data Index: 194776 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0781. Min Act: -0.0002

Data Index: 421382 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0686. Min Act: -0.0002

Data Index: 5179 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1309953 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1008406 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0683. Min Act: -0.0002

Data Index: 396111 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0674. Min Act: -0.0002

Data Index: 355532 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1312868 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0693. Min Act: -0.0002

Data Index: 840564 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0668. Min Act: -0.0002

Data Index: 294586 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0649. Min Act: -0.0002

Data Index: 379529 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0629. Min Act: -0.0002

Data Index: 383176 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1204 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0660. Min Act: -0.0002

Data Index: 479246 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1118488 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0619. Min Act: -0.0002

Data Index: 658652 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0630. Min Act: -0.0002

Data Index: 529865 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0629. Min Act: -0.0002

Data Index: 844431 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0638. Min Act: -0.0002

Data Index: 419786 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1189237 (C4 (Web Text))

Max Activating Token Index: 150