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

Dataset: The Pile

Neuron 91 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: 0.7877. Min Range: -0.7877

Max Act: 0.7877. Min Act: -0.0000

Data Index: 633494 (The Pile)

Max Activating Token Index: 314

Text #1

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1923287 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1029967 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1584475 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1822141 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1985449 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5519. Min Act: -0.0000

Data Index: 294043 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5841. Min Act: -0.0000

Data Index: 536650 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5499. Min Act: -0.0000

Data Index: 889395 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1785112 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5721. Min Act: -0.0000

Data Index: 873915 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5409. Min Act: -0.0000

Data Index: 769868 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5347. Min Act: -0.0000

Data Index: 883079 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1514891 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5477. Min Act: -0.0000

Data Index: 173537 (The Pile)

Max Activating Token Index: 766

Text #15

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5228. Min Act: -0.0000

Data Index: 791194 (The Pile)

Max Activating Token Index: 351

Text #16

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5201. Min Act: -0.0000

Data Index: 150488 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1253919 (The Pile)

Max Activating Token Index: 378

Text #18

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1888222 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5294. Min Act: -0.0000

Data Index: 139779 (The Pile)

Max Activating Token Index: 282