Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2948 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.9660. Min Act: -0.0000

Data Index: 1093238 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.9823. Min Act: -0.0000

Data Index: 36086 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.2293. Min Act: -0.0000

Data Index: 53248 (The Pile)

Max Activating Token Index: 681

Text #3

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.6918. Min Act: -0.0000

Data Index: 563268 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4867. Min Act: -0.0000

Data Index: 1760387 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4722. Min Act: -0.0000

Data Index: 915310 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.5274. Min Act: -0.0000

Data Index: 159961 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1128925 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.2828. Min Act: -0.0000

Data Index: 1441521 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1743360 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1896505 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.2182. Min Act: -0.0000

Data Index: 321630 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1247668 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1838029 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.1807. Min Act: -0.0000

Data Index: 279435 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4111. Min Act: -0.0000

Data Index: 437400 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.3037. Min Act: -0.0000

Data Index: 750348 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1986009 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.2017. Min Act: -0.0000

Data Index: 168647 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1480546 (The Pile)

Max Activating Token Index: 932