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

Dataset: The Pile

Neuron 1502 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: 1.0111. Min Range: -1.0111

Max Act: 0.9187. Min Act: -0.0000

Data Index: 760135 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1213856 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1025653 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1377386 (The Pile)

Max Activating Token Index: 543

Text #4

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1311799 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1393830 (The Pile)

Max Activating Token Index: 888

Text #6

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7461. Min Act: -0.0000

Data Index: 32916 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1807636 (The Pile)

Max Activating Token Index: 871

Text #8

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7232. Min Act: -0.0000

Data Index: 549632 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7616. Min Act: -0.0000

Data Index: 357598 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 1.0111. Min Range: -1.0111

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1508273 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1347685 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1494633 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6911. Min Act: -0.0000

Data Index: 965837 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6249. Min Act: -0.0000

Data Index: 737571 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1741479 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6432. Min Act: -0.0000

Data Index: 312512 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1155681 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.6659. Min Act: -0.0000

Data Index: 319170 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 1.0111. Min Range: -1.0111

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1195957 (The Pile)

Max Activating Token Index: 669