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

Dataset: The Pile

Neuron 1729 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: 1.0862. Min Range: -1.0862

Max Act: 1.0862. Min Act: -0.0000

Data Index: 85507 (The Pile)

Max Activating Token Index: 965

Text #1

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0809. Min Act: -0.0000

Data Index: 639269 (The Pile)

Max Activating Token Index: 1005

Text #2

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0268. Min Act: -0.0000

Data Index: 846246 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0167. Min Act: -0.0000

Data Index: 556707 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9865. Min Act: -0.0000

Data Index: 933561 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1810078 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9768. Min Act: -0.0000

Data Index: 820795 (The Pile)

Max Activating Token Index: 571

Text #7

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1868271 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9634. Min Act: -0.0000

Data Index: 135792 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1962217 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1764029 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1364331 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9343. Min Act: -0.0000

Data Index: 618299 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1197378 (The Pile)

Max Activating Token Index: 621

Text #14

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9240. Min Act: -0.0000

Data Index: 596328 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1460036 (The Pile)

Max Activating Token Index: 384

Text #16

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1698556 (The Pile)

Max Activating Token Index: 642

Text #17

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9189. Min Act: -0.0000

Data Index: 72284 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9071. Min Act: -0.0000

Data Index: 820217 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1643183 (The Pile)

Max Activating Token Index: 973