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

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

Neuron 639 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.2188. Min Act: -0.0000

Data Index: 702549 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.2109. Min Act: -0.0000

Data Index: 902009 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1240470 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1706. Min Act: -0.0000

Data Index: 54806 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1867. Min Act: -0.0000

Data Index: 972717 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1705. Min Act: -0.0000

Data Index: 76666 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1682. Min Act: -0.0000

Data Index: 501177 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1641. Min Act: -0.0000

Data Index: 134782 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1598. Min Act: -0.0000

Data Index: 505455 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1325599 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1635. Min Act: -0.0000

Data Index: 89298 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1623. Min Act: -0.0000

Data Index: 613988 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1573. Min Act: -0.0000

Data Index: 324908 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1613. Min Act: -0.0000

Data Index: 7972 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1580. Min Act: -0.0000

Data Index: 119385 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1577. Min Act: -0.0000

Data Index: 838777 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1568. Min Act: -0.0000

Data Index: 301340 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1502. Min Act: -0.0000

Data Index: 983417 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1470. Min Act: -0.0000

Data Index: 266714 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.2188. Min Range: -0.2188

Max Act: 0.1568. Min Act: -0.0000

Data Index: 335438 (C4 (Web Text))

Max Activating Token Index: 960