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

Dataset: The Pile

Neuron 3945 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1200. Min Range: -7.1200

Max Act: 7.1200. Min Act: -0.0000

Data Index: 346063 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.6346. Min Act: -0.0000

Data Index: 98491 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.1879. Min Act: -0.0000

Data Index: 259414 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.9171. Min Act: -0.0000

Data Index: 783433 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.5162. Min Act: -0.0000

Data Index: 1213000 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 7.1200. Min Range: -7.1200

Max Act: 7.0739. Min Act: -0.0000

Data Index: 1934136 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 7.1200. Min Range: -7.1200

Max Act: 5.7635. Min Act: -0.0000

Data Index: 1012205 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 7.1200. Min Range: -7.1200

Max Act: 5.4726. Min Act: -0.0000

Data Index: 432473 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.3732. Min Act: -0.0000

Data Index: 1619784 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 7.1200. Min Range: -7.1200

Max Act: 5.5981. Min Act: -0.0000

Data Index: 1117354 (The Pile)

Max Activating Token Index: 872

Text #10

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.3298. Min Act: -0.0000

Data Index: 729128 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 7.1200. Min Range: -7.1200

Max Act: 5.7068. Min Act: -0.0000

Data Index: 1085449 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.1828. Min Act: -0.0000

Data Index: 557317 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.2923. Min Act: -0.0000

Data Index: 1057568 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 7.1200. Min Range: -7.1200

Max Act: 5.6566. Min Act: -0.0000

Data Index: 1203993 (The Pile)

Max Activating Token Index: 681

Text #15

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.1603. Min Act: -0.0000

Data Index: 766142 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 7.1200. Min Range: -7.1200

Max Act: 5.3596. Min Act: -0.0000

Data Index: 660242 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 7.1200. Min Range: -7.1200

Max Act: 6.0681. Min Act: -0.0000

Data Index: 1898759 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 7.1200. Min Range: -7.1200

Max Act: 5.7941. Min Act: -0.0000

Data Index: 804873 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 7.1200. Min Range: -7.1200

Max Act: 5.4439. Min Act: -0.0000

Data Index: 29254 (The Pile)

Max Activating Token Index: 73