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

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

Neuron 4225 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: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0000

Data Index: 1416744 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1610651 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1476151 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1637811 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0708. Min Act: -0.0000

Data Index: 1474423 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0697. Min Act: -0.0000

Data Index: 633460 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0696. Min Act: -0.0000

Data Index: 850388 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1365512 (Python Code)

Max Activating Token Index: 52

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1270214 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0655. Min Act: -0.0000

Data Index: 517260 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1047221 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0636. Min Act: -0.0000

Data Index: 350844 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0659. Min Act: -0.0000

Data Index: 608997 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0631. Min Act: -0.0000

Data Index: 997574 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1656866 (Python Code)

Max Activating Token Index: 940

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0602. Min Act: -0.0000

Data Index: 39856 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1531009 (Python Code)

Max Activating Token Index: 913

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0623. Min Act: -0.0000

Data Index: 1174408 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0597. Min Act: -0.0000

Data Index: 49296 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1125352 (C4 (Web Text))

Max Activating Token Index: 738