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

Dataset: The Pile

Neuron 4342 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: 1.3623. Min Range: -1.3623

Max Act: 1.1130. Min Act: -0.0000

Data Index: 554389 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.3623. Min Act: -0.0000

Data Index: 488962 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1233029 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.5655. Min Act: -0.0000

Data Index: 994848 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1709874 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.5506. Min Act: -0.0000

Data Index: 57655 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1519204 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1719773 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1808483 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1541530 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1855799 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.5335. Min Act: -0.0000

Data Index: 551053 (The Pile)

Max Activating Token Index: 101

Text #12

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.5164. Min Act: -0.0000

Data Index: 86020 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1665057 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.4315. Min Act: -0.0000

Data Index: 166071 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1042998 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.4280. Min Act: -0.0000

Data Index: 207195 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1637630 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1823377 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 1.3623. Min Range: -1.3623

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1190483 (The Pile)

Max Activating Token Index: 907