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

Dataset: The Pile

Neuron 4766 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: 1.3003. Min Range: -1.3003

Max Act: 1.3003. Min Act: -0.0000

Data Index: 545937 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.2611. Min Act: -0.0000

Data Index: 1390132 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1650489 (The Pile)

Max Activating Token Index: 577

Text #3

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0609. Min Act: -0.0000

Data Index: 529577 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1983. Min Act: -0.0000

Data Index: 610867 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1475475 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9938. Min Act: -0.0000

Data Index: 518619 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1317328 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.8829. Min Act: 0.0000

Data Index: 833154 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9331. Min Act: 0.0000

Data Index: 1071620 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1817857 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9049. Min Act: -0.0000

Data Index: 124980 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9389. Min Act: -0.0000

Data Index: 989934 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1418697 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9247. Min Act: 0.0000

Data Index: 352244 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1044865 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1412564 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1785223 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.8493. Min Act: 0.0000

Data Index: 968017 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.8023. Min Act: -0.0000

Data Index: 475530 (The Pile)

Max Activating Token Index: 848