Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 441 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1709. Min Range: -1.1709

Max Act: 1.1709. Min Act: -0.0000

Data Index: 1520696 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 1.1709. Min Range: -1.1709

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1747526 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 1.1709. Min Range: -1.1709

Max Act: 1.0847. Min Act: -0.0000

Data Index: 293042 (The Pile)

Max Activating Token Index: 678

Text #3

Max Range: 1.1709. Min Range: -1.1709

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1081756 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9636. Min Act: -0.0000

Data Index: 835944 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9854. Min Act: -0.0000

Data Index: 337916 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 1.1709. Min Range: -1.1709

Max Act: 1.0084. Min Act: -0.0000

Data Index: 102695 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 1.1709. Min Range: -1.1709

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1524827 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1911126 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9598. Min Act: -0.0000

Data Index: 558092 (The Pile)

Max Activating Token Index: 506

Text #10

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1876071 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9242. Min Act: -0.0000

Data Index: 412319 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9212. Min Act: -0.0000

Data Index: 189729 (The Pile)

Max Activating Token Index: 844

Text #13

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1891820 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.8939. Min Act: -0.0000

Data Index: 814299 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1738133 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1973994 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9381. Min Act: -0.0000

Data Index: 290562 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1778974 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9357. Min Act: -0.0000

Data Index: 129830 (The Pile)

Max Activating Token Index: 352