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

Dataset: The Pile

Neuron 1964 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1678007 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.2046. Min Act: -0.0000

Data Index: 829303 (The Pile)

Max Activating Token Index: 840

Text #2

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1997844 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1664160 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1374794 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0550. Min Act: -0.0000

Data Index: 18420 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1066553 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0376. Min Act: -0.0000

Data Index: 893842 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1358367 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9462. Min Act: -0.0000

Data Index: 531679 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.1317. Min Act: -0.0000

Data Index: 1335390 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1896258 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9474. Min Act: -0.0000

Data Index: 996901 (The Pile)

Max Activating Token Index: 905

Text #13

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1415437 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0292. Min Act: -0.0000

Data Index: 435368 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8573. Min Act: -0.0000

Data Index: 347702 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9217. Min Act: -0.0000

Data Index: 723454 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1198545 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1781209 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8670. Min Act: -0.0000

Data Index: 492652 (The Pile)

Max Activating Token Index: 649