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

Dataset: The Pile

Neuron 3681 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1432249 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1881154 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1549426 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1725656 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0945. Min Act: -0.0000

Data Index: 62683 (The Pile)

Max Activating Token Index: 753

Text #5

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0877. Min Act: -0.0000

Data Index: 221391 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1448272 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1000743 (The Pile)

Max Activating Token Index: 94

Text #8

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1119. Min Act: -0.0000

Data Index: 1313185 (The Pile)

Max Activating Token Index: 25

Text #9

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0773. Min Act: -0.0000

Data Index: 191695 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1150. Min Act: -0.0000

Data Index: 1604096 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0953. Min Act: -0.0000

Data Index: 746612 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0896. Min Act: -0.0000

Data Index: 695176 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1302627 (The Pile)

Max Activating Token Index: 779

Text #14

Max Range: 1.3012. Min Range: -1.3012

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1847814 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1412437 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0843. Min Act: -0.0000

Data Index: 282614 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0704. Min Act: -0.0000

Data Index: 183219 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0445. Min Act: -0.0000

Data Index: 633290 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0351. Min Act: -0.0000

Data Index: 805653 (The Pile)

Max Activating Token Index: 176