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

Dataset: The Pile

Neuron 1610 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1281. Min Range: -1.1281

Max Act: 1.1281. Min Act: -0.0000

Data Index: 1715533 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 1.1281. Min Range: -1.1281

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1537659 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 1.1281. Min Range: -1.1281

Max Act: 1.0482. Min Act: -0.0000

Data Index: 230549 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1566175 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1660713 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.9374. Min Act: -0.0000

Data Index: 671995 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1947950 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.9731. Min Act: -0.0000

Data Index: 73715 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1246287 (The Pile)

Max Activating Token Index: 462

Text #9

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1183299 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.8653. Min Act: -0.0000

Data Index: 297987 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1103901 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.8623. Min Act: -0.0000

Data Index: 429226 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1914015 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.7067. Min Act: -0.0000

Data Index: 381408 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1470320 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.9295. Min Act: -0.0000

Data Index: 806045 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1485472 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1004006 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 1.1281. Min Range: -1.1281

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1013605 (The Pile)

Max Activating Token Index: 57