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

Dataset: The Pile

Neuron 2598 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: 1.0362. Min Range: -1.0362

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1080914 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1642700 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.9821. Min Act: -0.0000

Data Index: 409546 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1830154 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.7850. Min Act: -0.0000

Data Index: 62023 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1661048 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1448922 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.7111. Min Act: -0.0000

Data Index: 246653 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1285743 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.6556. Min Act: -0.0000

Data Index: 347605 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1583410 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.5794. Min Act: -0.0000

Data Index: 313079 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.6077. Min Act: -0.0000

Data Index: 829402 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1794407 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1050227 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.6262. Min Act: -0.0000

Data Index: 792219 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1174722 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.6495. Min Act: -0.0000

Data Index: 977498 (The Pile)

Max Activating Token Index: 878

Text #18

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1626020 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 1.0362. Min Range: -1.0362

Max Act: 0.5554. Min Act: -0.0000

Data Index: 707730 (The Pile)

Max Activating Token Index: 234