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

Dataset: The Pile

Neuron 469 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: 1.1898. Min Range: -1.1898

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1179600 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1954991 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9817. Min Act: -0.0000

Data Index: 557994 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1723765 (The Pile)

Max Activating Token Index: 994

Text #4

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7946. Min Act: -0.0000

Data Index: 51712 (The Pile)

Max Activating Token Index: 343

Text #5

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8359. Min Act: -0.0000

Data Index: 355302 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8139. Min Act: -0.0000

Data Index: 400980 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1660875 (The Pile)

Max Activating Token Index: 623

Text #8

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1106989 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7924. Min Act: -0.0000

Data Index: 657201 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1964730 (The Pile)

Max Activating Token Index: 392

Text #11

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7220. Min Act: -0.0000

Data Index: 60974 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1434418 (The Pile)

Max Activating Token Index: 933

Text #13

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1973038 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1336170 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.6950. Min Act: -0.0000

Data Index: 156858 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1622323 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1726118 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1452150 (The Pile)

Max Activating Token Index: 438

Text #19

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1573193 (The Pile)

Max Activating Token Index: 428