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

Dataset: The Pile

Neuron 971 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: 1.4037. Min Range: -1.4037

Max Act: 1.3900. Min Act: -0.0000

Data Index: 784447 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.3016. Min Act: -0.0000

Data Index: 679779 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.2963. Min Act: -0.0000

Data Index: 34485 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.4037. Min Act: -0.0000

Data Index: 1460759 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.2355. Min Act: -0.0000

Data Index: 1602405 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1871817 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.1100. Min Act: -0.0000

Data Index: 297343 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.1547. Min Act: -0.0000

Data Index: 119807 (The Pile)

Max Activating Token Index: 464

Text #8

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1910272 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1828182 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.1010. Min Act: -0.0000

Data Index: 828087 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1781230 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1604369 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0657. Min Act: -0.0000

Data Index: 906623 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0780. Min Act: -0.0000

Data Index: 756308 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0992. Min Act: -0.0000

Data Index: 235092 (The Pile)

Max Activating Token Index: 46

Text #16

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.1850. Min Act: -0.0000

Data Index: 517791 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0842. Min Act: -0.0000

Data Index: 636524 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 1.4037. Min Range: -1.4037

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1112681 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 1.4037. Min Range: -1.4037

Max Act: 0.9941. Min Act: -0.0000

Data Index: 198048 (The Pile)

Max Activating Token Index: 148