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

Dataset: The Pile

Neuron 5067 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: 3.3909. Min Range: -3.3909

Max Act: 3.3909. Min Act: -0.0000

Data Index: 1813071 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 3.3909. Min Range: -3.3909

Max Act: 3.2897. Min Act: -0.0000

Data Index: 730947 (The Pile)

Max Activating Token Index: 603

Text #2

Max Range: 3.3909. Min Range: -3.3909

Max Act: 3.2443. Min Act: -0.0000

Data Index: 1201366 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 3.3909. Min Range: -3.3909

Max Act: 3.0122. Min Act: -0.0000

Data Index: 1970776 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 3.3909. Min Range: -3.3909

Max Act: 3.0780. Min Act: -0.0000

Data Index: 315679 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 3.3909. Min Range: -3.3909

Max Act: 3.0406. Min Act: -0.0000

Data Index: 928070 (The Pile)

Max Activating Token Index: 738

Text #6

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.9410. Min Act: -0.0000

Data Index: 934987 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.9328. Min Act: -0.0000

Data Index: 854452 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.9454. Min Act: -0.0000

Data Index: 1017812 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 3.3909. Min Range: -3.3909

Max Act: 3.1725. Min Act: -0.0000

Data Index: 1136180 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.7156. Min Act: -0.0000

Data Index: 1515851 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.8276. Min Act: -0.0000

Data Index: 1503141 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.8045. Min Act: -0.0000

Data Index: 1203183 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.7580. Min Act: -0.0000

Data Index: 1514247 (The Pile)

Max Activating Token Index: 366

Text #14

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.8848. Min Act: -0.0000

Data Index: 1007463 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.7387. Min Act: -0.0000

Data Index: 1485324 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.5272. Min Act: -0.0000

Data Index: 248327 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.6207. Min Act: -0.0000

Data Index: 1814547 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.6248. Min Act: -0.0000

Data Index: 1433220 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 3.3909. Min Range: -3.3909

Max Act: 2.7302. Min Act: -0.0000

Data Index: 81535 (The Pile)

Max Activating Token Index: 766