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

Dataset: The Pile

Neuron 1247 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: 0.9828. Min Range: -0.9828

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1466446 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8719. Min Act: -0.0000

Data Index: 1537043 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8916. Min Act: -0.0000

Data Index: 557264 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1620985 (The Pile)

Max Activating Token Index: 313

Text #4

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1797067 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1241232 (The Pile)

Max Activating Token Index: 289

Text #6

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1006864 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8947. Min Act: -0.0000

Data Index: 40770 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1079531 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1368794 (The Pile)

Max Activating Token Index: 436

Text #10

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8109. Min Act: -0.0000

Data Index: 187785 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8248. Min Act: -0.0000

Data Index: 202551 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8195. Min Act: -0.0000

Data Index: 12891 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.7995. Min Act: -0.0000

Data Index: 136485 (The Pile)

Max Activating Token Index: 715

Text #14

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.7681. Min Act: -0.0000

Data Index: 775978 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1973151 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1238758 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1183756 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.7570. Min Act: 0.0000

Data Index: 370313 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.7588. Min Act: 0.0000

Data Index: 864406 (The Pile)

Max Activating Token Index: 437