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

Dataset: The Pile

Neuron 2041 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: 0.8044. Min Range: -0.8044

Max Act: 0.8044. Min Act: -0.0000

Data Index: 533805 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1259831 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.6252. Min Act: -0.0000

Data Index: 956017 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1003942 (The Pile)

Max Activating Token Index: 635

Text #4

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5693. Min Act: 0.0001

Data Index: 872355 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5295. Min Act: -0.0000

Data Index: 796147 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1326792 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5115. Min Act: 0.0000

Data Index: 1605208 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5235. Min Act: -0.0000

Data Index: 45625 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5124. Min Act: -0.0000

Data Index: 167629 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4761. Min Act: -0.0000

Data Index: 232270 (The Pile)

Max Activating Token Index: 659

Text #11

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1483423 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5028. Min Act: -0.0000

Data Index: 490690 (The Pile)

Max Activating Token Index: 913

Text #13

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1755495 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4919. Min Act: -0.0000

Data Index: 381100 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1695803 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4263. Min Act: -0.0000

Data Index: 135425 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1722526 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1435380 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1611995 (The Pile)

Max Activating Token Index: 929