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

Dataset: The Pile

Neuron 754 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: 1.1420. Min Range: -1.1420

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1423516 (The Pile)

Max Activating Token Index: 534

Text #1

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1847267 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1422649 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6746. Min Act: -0.0000

Data Index: 388240 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.7191. Min Act: -0.0000

Data Index: 936422 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1969129 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6828. Min Act: -0.0000

Data Index: 233248 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6927. Min Act: -0.0000

Data Index: 417413 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1590905 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6788. Min Act: -0.0000

Data Index: 555513 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6219. Min Act: -0.0000

Data Index: 426043 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1362372 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6063. Min Act: -0.0000

Data Index: 326110 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6398. Min Act: -0.0000

Data Index: 375851 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.5606. Min Act: -0.0000

Data Index: 420736 (The Pile)

Max Activating Token Index: 487

Text #15

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.5716. Min Act: -0.0000

Data Index: 630427 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1265591 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1858914 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1401907 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1881171 (The Pile)

Max Activating Token Index: 869