Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4992 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0920. Min Act: -0.0000

Data Index: 643611 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0778. Min Act: -0.0000

Data Index: 749054 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1605759 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1580195 (Python Code)

Max Activating Token Index: 254

Text #4

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1586517 (Python Code)

Max Activating Token Index: 339

Text #5

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1521110 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1428761 (Python Code)

Max Activating Token Index: 425

Text #7

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1515296 (Python Code)

Max Activating Token Index: 722

Text #8

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1606768 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1451586 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0628. Min Act: -0.0000

Data Index: 390693 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1392652 (Python Code)

Max Activating Token Index: 631

Text #12

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1395222 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0615. Min Act: -0.0000

Data Index: 271170 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1383184 (Python Code)

Max Activating Token Index: 499

Text #15

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1638733 (Python Code)

Max Activating Token Index: 1008

Text #16

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0630. Min Act: -0.0000

Data Index: 1587950 (Python Code)

Max Activating Token Index: 399

Text #17

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1381021 (Python Code)

Max Activating Token Index: 381

Text #18

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1576708 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0644. Min Act: -0.0000

Data Index: 424305 (C4 (Web Text))

Max Activating Token Index: 57