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

Dataset: The Pile

Neuron 495 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1022476 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5638. Min Act: -0.0000

Data Index: 431068 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1339965 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1885108 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1867439 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5134. Min Act: -0.0000

Data Index: 495580 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.3879. Min Act: -0.0000

Data Index: 226714 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1621773 (The Pile)

Max Activating Token Index: 365

Text #8

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.3856. Min Act: -0.0000

Data Index: 123968 (The Pile)

Max Activating Token Index: 875

Text #9

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4448. Min Act: -0.0000

Data Index: 853322 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1359366 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4027. Min Act: -0.0000

Data Index: 835884 (The Pile)

Max Activating Token Index: 514

Text #12

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4208. Min Act: -0.0000

Data Index: 484807 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4153. Min Act: -0.0000

Data Index: 130195 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4124. Min Act: -0.0000

Data Index: 416187 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1888153 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4129. Min Act: -0.0000

Data Index: 729218 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1679032 (The Pile)

Max Activating Token Index: 431

Text #18

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4001. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1038165 (The Pile)

Max Activating Token Index: 704