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

Dataset: The Pile

Neuron 1925 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: 0.8219. Min Range: -0.8219

Max Act: 0.7808. Min Act: -0.0000

Data Index: 341346 (The Pile)

Max Activating Token Index: 626

Text #1

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.8219. Min Act: -0.0000

Data Index: 815445 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7682. Min Act: -0.0000

Data Index: 252630 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6937. Min Act: -0.0000

Data Index: 325940 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7214. Min Act: -0.0000

Data Index: 43751 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1743481 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6897. Min Act: -0.0000

Data Index: 701032 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7672. Min Act: -0.0000

Data Index: 353486 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7526. Min Act: 0.0000

Data Index: 1768967 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1727288 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7172. Min Act: 0.0000

Data Index: 1028729 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6700. Min Act: -0.0000

Data Index: 531767 (The Pile)

Max Activating Token Index: 467

Text #12

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1603444 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6871. Min Act: -0.0000

Data Index: 659786 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6944. Min Act: -0.0000

Data Index: 819418 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1564243 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1086025 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1764088 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1658666 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1579120 (The Pile)

Max Activating Token Index: 565