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

Dataset: The Pile

Neuron 52 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: 0.1432. Min Range: -0.1432

Max Act: 0.1432. Min Act: -0.0000

Data Index: 54598 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1082721 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1739294 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1963241 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1333426 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1567165 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0924. Min Act: -0.0000

Data Index: 874428 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1366560 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0843. Min Act: -0.0000

Data Index: 826515 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0924. Min Act: -0.0000

Data Index: 160001 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1998234 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0849. Min Act: -0.0000

Data Index: 79483 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0792. Min Act: -0.0000

Data Index: 858176 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1794018 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0800. Min Act: -0.0000

Data Index: 347077 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0819. Min Act: -0.0000

Data Index: 188739 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1369403 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0753. Min Act: -0.0000

Data Index: 270686 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0718. Min Act: -0.0000

Data Index: 27926 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0793. Min Act: -0.0000

Data Index: 528558 (The Pile)

Max Activating Token Index: 246