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

Dataset: The Pile

Neuron 544 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1421. Min Range: -1.1421

Max Act: 1.1421. Min Act: -0.0000

Data Index: 202790 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 1.1421. Min Range: -1.1421

Max Act: 1.0457. Min Act: 0.0000

Data Index: 1847210 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 1.1421. Min Range: -1.1421

Max Act: 1.0639. Min Act: -0.0000

Data Index: 1558214 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.9150. Min Act: -0.0000

Data Index: 728141 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1124184 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.9236. Min Act: -0.0000

Data Index: 607020 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1083446 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1831714 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1246527 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1116940 (The Pile)

Max Activating Token Index: 50

Text #10

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8237. Min Act: -0.0000

Data Index: 407578 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1923592 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1850833 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1893660 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1669756 (The Pile)

Max Activating Token Index: 656

Text #15

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7221. Min Act: -0.0000

Data Index: 261814 (The Pile)

Max Activating Token Index: 880

Text #16

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1506424 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7173. Min Act: -0.0000

Data Index: 62697 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7385. Min Act: -0.0000

Data Index: 311544 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7518. Min Act: -0.0000

Data Index: 793165 (The Pile)

Max Activating Token Index: 991