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

Dataset: The Pile

Neuron 2097 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: 3.0017. Min Range: -3.0017

Max Act: 3.0017. Min Act: -0.0000

Data Index: 1378865 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.7152. Min Act: -0.0000

Data Index: 1573264 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.4155. Min Act: -0.0000

Data Index: 1938900 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.5832. Min Act: -0.0000

Data Index: 126114 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.5605. Min Act: -0.0000

Data Index: 1935925 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.5400. Min Act: -0.0000

Data Index: 1455180 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.5282. Min Act: -0.0000

Data Index: 1246619 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.3785. Min Act: -0.0000

Data Index: 1423189 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.3476. Min Act: -0.0000

Data Index: 1697133 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.4650. Min Act: -0.0000

Data Index: 396118 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.3191. Min Act: -0.0000

Data Index: 381210 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.6749. Min Act: -0.0000

Data Index: 874152 (The Pile)

Max Activating Token Index: 650

Text #12

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.1887. Min Act: -0.0000

Data Index: 233871 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.4332. Min Act: -0.0000

Data Index: 886850 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.4020. Min Act: -0.0000

Data Index: 1571730 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.3805. Min Act: -0.0000

Data Index: 1703714 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.2617. Min Act: -0.0000

Data Index: 1538856 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.2513. Min Act: -0.0000

Data Index: 559344 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.3638. Min Act: -0.0000

Data Index: 1860448 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.2363. Min Act: -0.0000

Data Index: 31368 (The Pile)

Max Activating Token Index: 263