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

Dataset: The Pile

Neuron 4191 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: 0.2642. Min Range: -0.2642

Max Act: 0.2642. Min Act: -0.0000

Data Index: 186102 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1186823 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1186304 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1569480 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1840795 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1809. Min Act: -0.0000

Data Index: 26145 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1439743 (The Pile)

Max Activating Token Index: 845

Text #7

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1433947 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1372955 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1986. Min Act: -0.0000

Data Index: 851245 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1860. Min Act: -0.0000

Data Index: 300273 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1707. Min Act: -0.0000

Data Index: 706541 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1633. Min Act: -0.0000

Data Index: 942107 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1908. Min Act: -0.0000

Data Index: 339037 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1930. Min Act: -0.0000

Data Index: 763032 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1437480 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1115827 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2254. Min Act: -0.0000

Data Index: 973349 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1867. Min Act: -0.0000

Data Index: 629301 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1689. Min Act: -0.0000

Data Index: 71321 (The Pile)

Max Activating Token Index: 504