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

Dataset: The Pile

Neuron 3792 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1212016 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1647147 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6990. Min Act: -0.0000

Data Index: 401957 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1700766 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1533736 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1246900 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6384. Min Act: -0.0000

Data Index: 950063 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5903. Min Act: -0.0000

Data Index: 889263 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1684902 (The Pile)

Max Activating Token Index: 991

Text #9

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5435. Min Act: -0.0000

Data Index: 725884 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6142. Min Act: -0.0000

Data Index: 929669 (The Pile)

Max Activating Token Index: 840

Text #11

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6354. Min Act: -0.0000

Data Index: 11260 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6150. Min Act: -0.0000

Data Index: 719599 (The Pile)

Max Activating Token Index: 880

Text #13

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6234. Min Act: -0.0000

Data Index: 989059 (The Pile)

Max Activating Token Index: 952

Text #14

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5640. Min Act: -0.0000

Data Index: 400816 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5620. Min Act: -0.0000

Data Index: 700286 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5615. Min Act: -0.0000

Data Index: 256823 (The Pile)

Max Activating Token Index: 617

Text #17

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1222821 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1581036 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1982768 (The Pile)

Max Activating Token Index: 290