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

Dataset: The Pile

Neuron 1053 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: 0.8167. Min Range: -0.8167

Max Act: 0.7993. Min Act: -0.0000

Data Index: 749682 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7315. Min Act: -0.0000

Data Index: 239195 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1157320 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7804. Min Act: -0.0000

Data Index: 696680 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7268. Min Act: -0.0000

Data Index: 337349 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1644885 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1912768 (The Pile)

Max Activating Token Index: 270

Text #7

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6202. Min Act: -0.0000

Data Index: 619160 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1741532 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7412. Min Act: -0.0000

Data Index: 681189 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6709. Min Act: -0.0000

Data Index: 145825 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1256993 (The Pile)

Max Activating Token Index: 455

Text #12

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6877. Min Act: -0.0000

Data Index: 785760 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6796. Min Act: -0.0000

Data Index: 803530 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1942091 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1720338 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6859. Min Act: -0.0000

Data Index: 606820 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1794787 (The Pile)

Max Activating Token Index: 538

Text #18

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6811. Min Act: -0.0000

Data Index: 989457 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6544. Min Act: -0.0000

Data Index: 517494 (The Pile)

Max Activating Token Index: 455