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

Dataset: The Pile

Neuron 3403 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1594974 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1109841 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1325399 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0975. Min Act: -0.0000

Data Index: 207494 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1742861 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0839. Min Act: 0.0000

Data Index: 1497646 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0850. Min Act: -0.0000

Data Index: 156917 (The Pile)

Max Activating Token Index: 728

Text #7

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1608811 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1367067 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1966334 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0806. Min Act: -0.0000

Data Index: 762590 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0755. Min Act: -0.0000

Data Index: 69017 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0770. Min Act: -0.0000

Data Index: 962608 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1842448 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0767. Min Act: -0.0000

Data Index: 988874 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0708. Min Act: -0.0000

Data Index: 776087 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1788381 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1240502 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1691546 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1569085 (The Pile)

Max Activating Token Index: 101