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

Dataset: The Pile

Neuron 3223 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0534. Min Range: -1.0534

Max Act: 1.0534. Min Act: -0.0000

Data Index: 210725 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.9940. Min Act: -0.0000

Data Index: 236101 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1727506 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1785087 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1087406 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1512376 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7541. Min Act: -0.0000

Data Index: 100167 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7715. Min Act: -0.0000

Data Index: 782133 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7446. Min Act: -0.0000

Data Index: 195467 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1138489 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1891399 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1893222 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7498. Min Act: -0.0000

Data Index: 855796 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.8023. Min Act: -0.0000

Data Index: 374856 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7709. Min Act: -0.0000

Data Index: 30902 (The Pile)

Max Activating Token Index: 620

Text #15

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7540. Min Act: -0.0000

Data Index: 329966 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7473. Min Act: -0.0000

Data Index: 846407 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1527178 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1505058 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 1.0534. Min Range: -1.0534

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1238253 (The Pile)

Max Activating Token Index: 580