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

Dataset: The Pile

Neuron 267 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.6171. Min Act: -0.0000

Data Index: 1746684 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.7375. Min Act: -0.0000

Data Index: 1180782 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.5768. Min Act: -0.0000

Data Index: 1952940 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.1359. Min Act: -0.0000

Data Index: 761515 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.5197. Min Act: -0.0000

Data Index: 816711 (The Pile)

Max Activating Token Index: 711

Text #5

Max Range: 5.7375. Min Range: -5.7375

Max Act: 4.8972. Min Act: -0.0000

Data Index: 1798361 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.6454. Min Act: -0.0000

Data Index: 615952 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.2634. Min Act: -0.0000

Data Index: 1486002 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.0745. Min Act: -0.0000

Data Index: 702332 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.4292. Min Act: -0.0000

Data Index: 128514 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.1348. Min Act: -0.0000

Data Index: 1712552 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 5.7375. Min Range: -5.7375

Max Act: 4.8891. Min Act: -0.0000

Data Index: 818513 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 5.7375. Min Range: -5.7375

Max Act: 4.8729. Min Act: -0.0000

Data Index: 850452 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.2600. Min Act: -0.0000

Data Index: 1573237 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.0077. Min Act: -0.0000

Data Index: 650725 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 5.7375. Min Range: -5.7375

Max Act: 5.0164. Min Act: -0.0000

Data Index: 1761480 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 5.7375. Min Range: -5.7375

Max Act: 4.9517. Min Act: -0.0000

Data Index: 1682863 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 5.7375. Min Range: -5.7375

Max Act: 4.7808. Min Act: -0.0000

Data Index: 1728854 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 5.7375. Min Range: -5.7375

Max Act: 4.8962. Min Act: -0.0000

Data Index: 1353529 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 5.7375. Min Range: -5.7375

Max Act: 4.5248. Min Act: -0.0000

Data Index: 675886 (The Pile)

Max Activating Token Index: 41