Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1925 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6778. Min Act: -0.0000

Data Index: 239830 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6285. Min Act: -0.0000

Data Index: 512118 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6215. Min Act: -0.0000

Data Index: 784706 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1340411 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1003123 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5481. Min Act: -0.0000

Data Index: 779405 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1112079 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5405. Min Act: 0.0001

Data Index: 501710 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5220. Min Act: -0.0000

Data Index: 303900 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5237. Min Act: -0.0000

Data Index: 303120 (The Pile)

Max Activating Token Index: 436

Text #10

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1574487 (The Pile)

Max Activating Token Index: 497

Text #11

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1405464 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4964. Min Act: -0.0000

Data Index: 725454 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1323827 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4719. Min Act: -0.0000

Data Index: 65215 (The Pile)

Max Activating Token Index: 26

Text #15

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1369840 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1078655 (The Pile)

Max Activating Token Index: 897

Text #17

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4715. Min Act: -0.0000

Data Index: 477914 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1707411 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4801. Min Act: 0.0001

Data Index: 110482 (The Pile)

Max Activating Token Index: 135