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

Dataset: The Pile

Neuron 1604 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: 3.8974. Min Range: -3.8974

Max Act: 3.8974. Min Act: -0.0000

Data Index: 826176 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.8400. Min Act: -0.0000

Data Index: 1238983 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.7790. Min Act: -0.0000

Data Index: 873602 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.7422. Min Act: -0.0000

Data Index: 785263 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.6544. Min Act: -0.0000

Data Index: 3023 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.6216. Min Act: -0.0000

Data Index: 1343202 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.4540. Min Act: -0.0000

Data Index: 235571 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.5869. Min Act: -0.0000

Data Index: 524657 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.5286. Min Act: -0.0000

Data Index: 1313890 (The Pile)

Max Activating Token Index: 956

Text #9

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.7883. Min Act: -0.0000

Data Index: 1048852 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.4088. Min Act: -0.0000

Data Index: 248692 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.4042. Min Act: -0.0000

Data Index: 405414 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.3784. Min Act: -0.0000

Data Index: 878264 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.3875. Min Act: -0.0000

Data Index: 35332 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.3658. Min Act: -0.0000

Data Index: 885422 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.4949. Min Act: -0.0000

Data Index: 281029 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.3483. Min Act: -0.0000

Data Index: 840241 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.5067. Min Act: -0.0000

Data Index: 503314 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.5264. Min Act: -0.0000

Data Index: 1572715 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 3.8974. Min Range: -3.8974

Max Act: 3.3262. Min Act: -0.0000

Data Index: 849165 (The Pile)

Max Activating Token Index: 534