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

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

Neuron 4437 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: 0.0695. Min Range: -0.0695

Max Act: 0.0695. Min Act: -0.0002

Data Index: 278977 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0688. Min Act: -0.0002

Data Index: 726370 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0677. Min Act: -0.0002

Data Index: 108359 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0648. Min Act: -0.0002

Data Index: 11014 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0620. Min Act: -0.0002

Data Index: 523858 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0622. Min Act: -0.0002

Data Index: 913545 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0630. Min Act: -0.0002

Data Index: 705994 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1427138 (Python Code)

Max Activating Token Index: 417

Text #8

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0563. Min Act: -0.0002

Data Index: 15455 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1231273 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0567. Min Act: -0.0002

Data Index: 745807 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0573. Min Act: -0.0002

Data Index: 765295 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0539. Min Act: -0.0002

Data Index: 529200 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0555. Min Act: -0.0002

Data Index: 776312 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0537. Min Act: -0.0002

Data Index: 507932 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1316206 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0527. Min Act: -0.0002

Data Index: 794204 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0523. Min Act: -0.0002

Data Index: 719681 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0504. Min Act: -0.0002

Data Index: 695739 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0524. Min Act: -0.0002

Data Index: 188096 (C4 (Web Text))

Max Activating Token Index: 242