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

Dataset: The Pile

Neuron 454 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1970355 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1765230 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6116. Min Act: -0.0000

Data Index: 965192 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1345182 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6649. Min Act: -0.0000

Data Index: 923980 (The Pile)

Max Activating Token Index: 1018

Text #5

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1016291 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1776973 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1692942 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5360. Min Act: -0.0000

Data Index: 761296 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5045. Min Act: 0.0000

Data Index: 809843 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1788110 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4785. Min Act: -0.0000

Data Index: 598806 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1375118 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4689. Min Act: -0.0000

Data Index: 953108 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4807. Min Act: -0.0000

Data Index: 176717 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1233656 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4467. Min Act: -0.0000

Data Index: 77437 (The Pile)

Max Activating Token Index: 588

Text #17

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4379. Min Act: -0.0000

Data Index: 690613 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4641. Min Act: -0.0000

Data Index: 240068 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1013438 (The Pile)

Max Activating Token Index: 442