Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1462 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1527. Min Act: -0.0001

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1236. Min Act: -0.0003

Data Index: 1033360 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0899. Min Act: -0.0002

Data Index: 347665 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0953. Min Act: -0.0001

Data Index: 329755 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0865. Min Act: -0.0003

Data Index: 907201 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0831. Min Act: -0.0002

Data Index: 389796 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0760. Min Act: -0.0001

Data Index: 458340 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0707. Min Act: -0.0003

Data Index: 1210740 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0823. Min Act: -0.0003

Data Index: 986008 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0556. Min Act: -0.0002

Data Index: 45430 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1609439 (Python Code)

Max Activating Token Index: 147

Text #11

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0481. Min Act: -0.0003

Data Index: 908832 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1050373 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0517. Min Act: -0.0002

Data Index: 974596 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0525. Min Act: -0.0002

Data Index: 708856 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0507. Min Act: -0.0003

Data Index: 80623 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1349802 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0494. Min Act: -0.0003

Data Index: 939805 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1023566 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.0504. Min Act: -0.0001

Data Index: 493417 (C4 (Web Text))

Max Activating Token Index: 773