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

Dataset: The Pile

Neuron 480 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: 1.1260. Min Range: -1.1260

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1316063 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1410629 (The Pile)

Max Activating Token Index: 386

Text #2

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9809. Min Act: -0.0000

Data Index: 567510 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1630272 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1467924 (The Pile)

Max Activating Token Index: 827

Text #5

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9746. Min Act: -0.0000

Data Index: 315823 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7896. Min Act: -0.0000

Data Index: 687226 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.0070. Min Act: -0.0000

Data Index: 710638 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.8394. Min Act: -0.0000

Data Index: 714800 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7377. Min Act: -0.0000

Data Index: 841301 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1855273 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1754369 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1538779 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1951548 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1380480 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1488733 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7206. Min Act: -0.0000

Data Index: 72035 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7659. Min Act: -0.0000

Data Index: 344671 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7899. Min Act: -0.0000

Data Index: 605338 (The Pile)

Max Activating Token Index: 973

Text #19

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7293. Min Act: -0.0000

Data Index: 813727 (The Pile)

Max Activating Token Index: 386