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

Dataset: The Pile

Neuron 755 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1194412 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5571. Min Act: -0.0000

Data Index: 108855 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1280008 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1106661 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4482. Min Act: -0.0000

Data Index: 193764 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4266. Min Act: -0.0000

Data Index: 498276 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1366466 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4129. Min Act: -0.0000

Data Index: 807689 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1681389 (The Pile)

Max Activating Token Index: 25

Text #9

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3356. Min Act: -0.0000

Data Index: 131676 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4005. Min Act: -0.0000

Data Index: 980895 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1855917 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1879707 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3605. Min Act: -0.0000

Data Index: 918154 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1655495 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3375. Min Act: -0.0000

Data Index: 919438 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1435978 (The Pile)

Max Activating Token Index: 121

Text #17

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3350. Min Act: -0.0000

Data Index: 386897 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1334122 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1689445 (The Pile)

Max Activating Token Index: 915