Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1432 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1086168 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1465249 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1377337 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1411306 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1640906 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1640255 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1337913 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1378622 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0513. Min Act: -0.0002

Data Index: 981853 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1653727 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0516. Min Act: -0.0002

Data Index: 550696 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1508517 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0492. Min Act: -0.0002

Data Index: 911516 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1604019 (Python Code)

Max Activating Token Index: 45

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1580827 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0491. Min Act: -0.0001

Data Index: 386429 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1500224 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1539916 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1365508 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1411605 (Python Code)

Max Activating Token Index: 28