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

Dataset: The Pile

Neuron 4775 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.1485. Min Act: -0.0000

Data Index: 3142 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1144700 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9629. Min Act: -0.0000

Data Index: 938982 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9127. Min Act: -0.0000

Data Index: 195076 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1397320 (The Pile)

Max Activating Token Index: 713

Text #5

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1156801 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.8726. Min Act: -0.0000

Data Index: 139375 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7838. Min Act: 0.0000

Data Index: 1479275 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7967. Min Act: 0.0000

Data Index: 1537667 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.8043. Min Act: -0.0000

Data Index: 421943 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.8057. Min Act: 0.0000

Data Index: 511092 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1847946 (The Pile)

Max Activating Token Index: 47

Text #12

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1661519 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1826457 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1606144 (The Pile)

Max Activating Token Index: 739

Text #15

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7215. Min Act: -0.0000

Data Index: 905462 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7730. Min Act: 0.0000

Data Index: 725814 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7523. Min Act: -0.0000

Data Index: 522525 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7434. Min Act: -0.0000

Data Index: 765726 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1058468 (The Pile)

Max Activating Token Index: 865