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

Dataset: The Pile

Neuron 1061 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: 1.4568. Min Range: -1.4568

Max Act: 1.4568. Min Act: -0.0000

Data Index: 748132 (The Pile)

Max Activating Token Index: 279

Text #1

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3194. Min Act: -0.0000

Data Index: 1359360 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3456. Min Act: -0.0000

Data Index: 945591 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.4199. Min Act: -0.0000

Data Index: 1899427 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3976. Min Act: -0.0000

Data Index: 860659 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3170. Min Act: -0.0000

Data Index: 515470 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3122. Min Act: -0.0000

Data Index: 603522 (The Pile)

Max Activating Token Index: 697

Text #7

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1296236 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1412700 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1347148 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0492. Min Act: -0.0000

Data Index: 926692 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1194. Min Act: -0.0000

Data Index: 225263 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1019. Min Act: -0.0000

Data Index: 1765881 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0544. Min Act: -0.0000

Data Index: 123168 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1295. Min Act: -0.0000

Data Index: 660037 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0366. Min Act: -0.0000

Data Index: 242872 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1130096 (The Pile)

Max Activating Token Index: 492

Text #17

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0420. Min Act: -0.0000

Data Index: 507950 (The Pile)

Max Activating Token Index: 28

Text #18

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0728. Min Act: -0.0000

Data Index: 822001 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1414291 (The Pile)

Max Activating Token Index: 471