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

Dataset: The Pile

Neuron 3352 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1783540 (The Pile)

Max Activating Token Index: 17

Text #1

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6471. Min Act: -0.0000

Data Index: 978126 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1876300 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4640. Min Act: -0.0000

Data Index: 165676 (The Pile)

Max Activating Token Index: 748

Text #4

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5624. Min Act: -0.0000

Data Index: 128946 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1578842 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1419241 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4098. Min Act: -0.0000

Data Index: 606979 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1140709 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1616716 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4240. Min Act: -0.0000

Data Index: 567357 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1630496 (The Pile)

Max Activating Token Index: 427

Text #12

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1273483 (The Pile)

Max Activating Token Index: 489

Text #13

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4300. Min Act: -0.0000

Data Index: 809979 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1879654 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1808513 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4020. Min Act: -0.0000

Data Index: 560241 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1764154 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1995238 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1002359 (The Pile)

Max Activating Token Index: 330