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

Dataset: The Pile

Neuron 3608 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.7729. Min Act: -0.0000

Data Index: 1788813 (The Pile)

Max Activating Token Index: 379

Text #1

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.9392. Min Act: -0.0000

Data Index: 1347707 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.6134. Min Act: -0.0000

Data Index: 944854 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.3172. Min Act: -0.0000

Data Index: 599285 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.6068. Min Act: -0.0000

Data Index: 1639238 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1370313 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.5371. Min Act: -0.0000

Data Index: 321630 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.1859. Min Act: -0.0000

Data Index: 157242 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.0833. Min Act: -0.0000

Data Index: 559793 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.2086. Min Act: -0.0000

Data Index: 918271 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.2432. Min Act: -0.0000

Data Index: 989568 (The Pile)

Max Activating Token Index: 672

Text #11

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1596747 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1543502 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1185043 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.0494. Min Act: -0.0000

Data Index: 470073 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 1.9392. Min Range: -1.9392

Max Act: 0.9147. Min Act: -0.0000

Data Index: 751238 (The Pile)

Max Activating Token Index: 519

Text #16

Max Range: 1.9392. Min Range: -1.9392

Max Act: 1.0186. Min Act: -0.0000

Data Index: 709893 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 1.9392. Min Range: -1.9392

Max Act: 0.7613. Min Act: -0.0000

Data Index: 315746 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 1.9392. Min Range: -1.9392

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1574177 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 1.9392. Min Range: -1.9392

Max Act: 0.1798. Min Act: -0.0000

Data Index: 44214 (The Pile)

Max Activating Token Index: 770