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

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

Neuron 1984 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0659. Min Act: -0.0002

Data Index: 801415 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1436089 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0607. Min Act: -0.0002

Data Index: 795060 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1292774 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1224860 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0478. Min Act: -0.0002

Data Index: 831220 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0523. Min Act: -0.0002

Data Index: 681694 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0529. Min Act: -0.0002

Data Index: 187033 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0490. Min Act: -0.0002

Data Index: 755943 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1387059 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1109876 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0480. Min Act: -0.0002

Data Index: 140873 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1015855 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1563920 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1607428 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0544. Min Act: -0.0002

Data Index: 184566 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1313534 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0487. Min Act: -0.0002

Data Index: 721944 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0498. Min Act: -0.0002

Data Index: 626619 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0466. Min Act: -0.0002

Data Index: 320234 (C4 (Web Text))

Max Activating Token Index: 962