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

Dataset: The Pile

Neuron 900 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: 0.7917. Min Range: -0.7917

Max Act: 0.7726. Min Act: -0.0000

Data Index: 209925 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.7712. Min Act: -0.0000

Data Index: 222002 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.7917. Min Act: -0.0000

Data Index: 187478 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1192090 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1727190 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1227903 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1710365 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1011232 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1832318 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1720361 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1225844 (The Pile)

Max Activating Token Index: 413

Text #11

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6368. Min Act: -0.0000

Data Index: 488850 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1225274 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6045. Min Act: -0.0000

Data Index: 20568 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1861638 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.5582. Min Act: -0.0000

Data Index: 523437 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.5772. Min Act: -0.0000

Data Index: 978932 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.5768. Min Act: -0.0000

Data Index: 571815 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1250167 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1276154 (The Pile)

Max Activating Token Index: 196