Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 811 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1896363 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7731. Min Act: -0.0000

Data Index: 428672 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7429. Min Act: -0.0000

Data Index: 940028 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6942. Min Act: -0.0000

Data Index: 884995 (The Pile)

Max Activating Token Index: 412

Text #4

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6648. Min Act: -0.0000

Data Index: 72523 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6555. Min Act: -0.0000

Data Index: 116505 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6791. Min Act: -0.0000

Data Index: 476453 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6256. Min Act: -0.0000

Data Index: 453636 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6477. Min Act: -0.0000

Data Index: 76892 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1393723 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6564. Min Act: -0.0000

Data Index: 902970 (The Pile)

Max Activating Token Index: 70

Text #11

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1979370 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1218769 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1980675 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6142. Min Act: -0.0000

Data Index: 950433 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1080865 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6104. Min Act: -0.0000

Data Index: 165142 (The Pile)

Max Activating Token Index: 854

Text #17

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1930855 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.5666. Min Act: -0.0000

Data Index: 316417 (The Pile)

Max Activating Token Index: 626

Text #19

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1635821 (The Pile)

Max Activating Token Index: 714