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

Dataset: The Pile

Neuron 692 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: 1.0478. Min Range: -1.0478

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1054934 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7880. Min Act: -0.0000

Data Index: 117974 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6977. Min Act: -0.0000

Data Index: 411108 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1839152 (The Pile)

Max Activating Token Index: 657

Text #4

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1420172 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7136. Min Act: -0.0000

Data Index: 464478 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1491653 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6398. Min Act: -0.0000

Data Index: 310876 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1320293 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1298615 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6626. Min Act: -0.0000

Data Index: 44966 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1220010 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6432. Min Act: -0.0000

Data Index: 109280 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1824997 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1149629 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1893137 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6419. Min Act: -0.0000

Data Index: 806923 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5795. Min Act: -0.0000

Data Index: 803403 (The Pile)

Max Activating Token Index: 216

Text #18

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1449724 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1099497 (The Pile)

Max Activating Token Index: 157