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

Dataset: The Pile

Neuron 1370 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1629016 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3934. Min Act: -0.0000

Data Index: 555239 (The Pile)

Max Activating Token Index: 802

Text #2

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1752947 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3632. Min Act: -0.0000

Data Index: 423418 (The Pile)

Max Activating Token Index: 600

Text #4

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3438. Min Act: -0.0000

Data Index: 958594 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1911251 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3192. Min Act: -0.0000

Data Index: 874388 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1253621 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3146. Min Act: -0.0000

Data Index: 605580 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3132. Min Act: 0.0000

Data Index: 585693 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3061. Min Act: -0.0000

Data Index: 349930 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3124. Min Act: -0.0000

Data Index: 950387 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1144209 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1413018 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1710757 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1206776 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.2928. Min Act: -0.0000

Data Index: 608103 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1988061 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1641460 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 0.4315. Min Range: -0.4315

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1956454 (The Pile)

Max Activating Token Index: 406