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

Dataset: The Pile

Neuron 2653 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: 0.6920. Min Range: -0.6920

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1650426 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1532759 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6761. Min Act: -0.0000

Data Index: 405711 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6731. Min Act: -0.0000

Data Index: 655744 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6456. Min Act: -0.0000

Data Index: 203996 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5513. Min Act: -0.0000

Data Index: 121453 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1563604 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5480. Min Act: -0.0000

Data Index: 705129 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5623. Min Act: -0.0000

Data Index: 459900 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1821227 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1554295 (The Pile)

Max Activating Token Index: 156

Text #11

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5266. Min Act: -0.0000

Data Index: 938635 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5051. Min Act: -0.0000

Data Index: 575333 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5333. Min Act: -0.0000

Data Index: 645633 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1107259 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1011846 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1771513 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5058. Min Act: -0.0000

Data Index: 395925 (The Pile)

Max Activating Token Index: 894

Text #18

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.4834. Min Act: -0.0000

Data Index: 941189 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.4667. Min Act: -0.0000

Data Index: 113776 (The Pile)

Max Activating Token Index: 855