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

Dataset: The Pile

Neuron 3985 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.1362. Min Act: -0.0000

Data Index: 395718 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.1096. Min Act: -0.0000

Data Index: 664999 (The Pile)

Max Activating Token Index: 386

Text #2

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1727173 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1774036 (The Pile)

Max Activating Token Index: 766

Text #4

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0534. Min Act: -0.0000

Data Index: 304085 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1860176 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1452121 (The Pile)

Max Activating Token Index: 679

Text #7

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9663. Min Act: -0.0000

Data Index: 729110 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1061504 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9299. Min Act: -0.0000

Data Index: 242117 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1790604 (The Pile)

Max Activating Token Index: 770

Text #11

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9944. Min Act: -0.0000

Data Index: 443470 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9106. Min Act: -0.0000

Data Index: 992420 (The Pile)

Max Activating Token Index: 709

Text #13

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9589. Min Act: -0.0000

Data Index: 735152 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.8337. Min Act: -0.0000

Data Index: 328669 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9234. Min Act: -0.0000

Data Index: 896985 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1824552 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1327458 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1725855 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1200048 (The Pile)

Max Activating Token Index: 200