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

Dataset: The Pile

Neuron 2600 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: 0.6018. Min Range: -0.6018

Max Act: 0.5994. Min Act: -0.0000

Data Index: 855574 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1028722 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1484606 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.5381. Min Act: -0.0000

Data Index: 522282 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.5397. Min Act: -0.0000

Data Index: 496218 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1141806 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4796. Min Act: -0.0000

Data Index: 41631 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4779. Min Act: -0.0000

Data Index: 926837 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4881. Min Act: -0.0000

Data Index: 914911 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4669. Min Act: -0.0000

Data Index: 35445 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1199049 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3980. Min Act: -0.0000

Data Index: 102131 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1493704 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1156389 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1471619 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4242. Min Act: -0.0000

Data Index: 37158 (The Pile)

Max Activating Token Index: 642

Text #16

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3598. Min Act: -0.0000

Data Index: 221012 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1303011 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1234986 (The Pile)

Max Activating Token Index: 563

Text #19

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1254836 (The Pile)

Max Activating Token Index: 959