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

Dataset: The Pile

Neuron 1442 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1302413 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5298. Min Act: -0.0000

Data Index: 139972 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1701720 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1651906 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1459128 (The Pile)

Max Activating Token Index: 599

Text #5

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1224086 (The Pile)

Max Activating Token Index: 921

Text #6

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1415885 (The Pile)

Max Activating Token Index: 413

Text #7

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4782. Min Act: -0.0000

Data Index: 238739 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4408. Min Act: -0.0000

Data Index: 248495 (The Pile)

Max Activating Token Index: 842

Text #9

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4618. Min Act: -0.0000

Data Index: 648495 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4357. Min Act: -0.0000

Data Index: 765475 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1597082 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4369. Min Act: -0.0000

Data Index: 787495 (The Pile)

Max Activating Token Index: 693

Text #13

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4061. Min Act: -0.0000

Data Index: 145258 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4061. Min Act: -0.0000

Data Index: 830210 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1487528 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1464047 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1545898 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1600626 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1946747 (The Pile)

Max Activating Token Index: 232