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

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

Neuron 2029 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.2192. Min Act: -0.0000

Data Index: 745445 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.2033. Min Act: -0.0001

Data Index: 609223 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1981. Min Act: -0.0000

Data Index: 761512 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.2045. Min Act: -0.0000

Data Index: 906083 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1976. Min Act: -0.0000

Data Index: 527780 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1750. Min Act: -0.0000

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1675. Min Act: -0.0000

Data Index: 275558 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1623. Min Act: -0.0000

Data Index: 707691 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1588. Min Act: -0.0000

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1647. Min Act: -0.0000

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1003173 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1415. Min Act: -0.0000

Data Index: 992196 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1669. Min Act: -0.0000

Data Index: 22883 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1418. Min Act: -0.0000

Data Index: 678639 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1648103 (Python Code)

Max Activating Token Index: 850

Text #16

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1465. Min Act: -0.0001

Data Index: 150372 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1071614 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1345706 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1616. Min Act: -0.0001

Data Index: 746089 (C4 (Web Text))

Max Activating Token Index: 335