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

Dataset: The Pile

Neuron 90 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: 0.8648. Min Range: -0.8648

Max Act: 0.8218. Min Act: -0.0000

Data Index: 952285 (The Pile)

Max Activating Token Index: 723

Text #1

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8648. Min Act: -0.0000

Data Index: 870691 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6951. Min Act: -0.0000

Data Index: 491356 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6022. Min Act: -0.0000

Data Index: 433740 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1228478 (The Pile)

Max Activating Token Index: 785

Text #5

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7037. Min Act: -0.0000

Data Index: 134483 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1487230 (The Pile)

Max Activating Token Index: 367

Text #7

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1313996 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1949761 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1461704 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1822212 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5112. Min Act: -0.0000

Data Index: 933089 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5381. Min Act: -0.0000

Data Index: 220940 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1200903 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1751741 (The Pile)

Max Activating Token Index: 563

Text #15

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6241. Min Act: -0.0000

Data Index: 79491 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6449. Min Act: -0.0000

Data Index: 624391 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1581495 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6010. Min Act: -0.0000

Data Index: 636542 (The Pile)

Max Activating Token Index: 879

Text #19

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5328. Min Act: -0.0000

Data Index: 532699 (The Pile)

Max Activating Token Index: 859