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

Dataset: The Pile

Neuron 2348 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: 1.4898. Min Range: -1.4898

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1896580 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.4898. Min Act: -0.0000

Data Index: 422223 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.3247. Min Act: -0.0000

Data Index: 730611 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.2681. Min Act: -0.0000

Data Index: 490926 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1336134 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.4621. Min Act: -0.0000

Data Index: 1695449 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0858. Min Act: -0.0000

Data Index: 975231 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1041512 (The Pile)

Max Activating Token Index: 910

Text #8

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.2305. Min Act: -0.0000

Data Index: 134471 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1450915 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1935228 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1279127 (The Pile)

Max Activating Token Index: 470

Text #12

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0911. Min Act: -0.0000

Data Index: 684097 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9556. Min Act: -0.0000

Data Index: 608681 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9873. Min Act: -0.0000

Data Index: 575539 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1005238 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9691. Min Act: -0.0000

Data Index: 243695 (The Pile)

Max Activating Token Index: 436

Text #17

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1666232 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1835895 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1303618 (The Pile)

Max Activating Token Index: 227