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

Dataset: The Pile

Neuron 5037 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1250272 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1236404 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1281441 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.9835. Min Act: -0.0000

Data Index: 40653 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0196. Min Act: -0.0000

Data Index: 570139 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1569302 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1293941 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1688807 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8362. Min Act: 0.0000

Data Index: 330032 (The Pile)

Max Activating Token Index: 875

Text #9

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1417994 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8002. Min Act: -0.0000

Data Index: 56782 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1738857 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8479. Min Act: -0.0000

Data Index: 702432 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.9152. Min Act: -0.0000

Data Index: 929999 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1079798 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8338. Min Act: -0.0000

Data Index: 384911 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1489475 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8927. Min Act: -0.0000

Data Index: 574605 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.8127. Min Act: 0.0000

Data Index: 1943132 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 1.3587. Min Range: -1.3587

Max Act: 0.7980. Min Act: -0.0000

Data Index: 45999 (The Pile)

Max Activating Token Index: 192