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

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

Neuron 3006 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1423363 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1384613 (Python Code)

Max Activating Token Index: 981

Text #2

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1527783 (Python Code)

Max Activating Token Index: 173

Text #3

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1616004 (Python Code)

Max Activating Token Index: 110

Text #4

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1407008 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1463993 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1548563 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1445317 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1602498 (Python Code)

Max Activating Token Index: 222

Text #9

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1486148 (Python Code)

Max Activating Token Index: 486

Text #10

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1656805 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1426122 (Python Code)

Max Activating Token Index: 838

Text #12

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1531777 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1567834 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1473471 (Python Code)

Max Activating Token Index: 331

Text #15

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1629487 (Python Code)

Max Activating Token Index: 569

Text #16

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1604248 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1370391 (Python Code)

Max Activating Token Index: 937

Text #18

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1481955 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1534954 (Python Code)

Max Activating Token Index: 104