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

Dataset: The Pile

Neuron 796 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: 0.2695. Min Range: -0.2695

Max Act: 0.2686. Min Act: -0.0000

Data Index: 185745 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2459. Min Act: -0.0000

Data Index: 643611 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2695. Min Act: -0.0000

Data Index: 541351 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2174. Min Act: -0.0000

Data Index: 132378 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2015. Min Act: -0.0000

Data Index: 716320 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1991451 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1282268 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2020. Min Act: -0.0000

Data Index: 406156 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1746. Min Act: -0.0000

Data Index: 823123 (The Pile)

Max Activating Token Index: 712

Text #9

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1915. Min Act: -0.0000

Data Index: 364657 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1968337 (The Pile)

Max Activating Token Index: 950

Text #11

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1696805 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1739. Min Act: -0.0000

Data Index: 516057 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1464303 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1852231 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1740. Min Act: -0.0000

Data Index: 540292 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1494627 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1643. Min Act: -0.0000

Data Index: 813481 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1228327 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1642. Min Act: -0.0000

Data Index: 73927 (The Pile)

Max Activating Token Index: 146