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

Dataset: The Pile

Neuron 1188 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0397. Min Range: -1.0397

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1893000 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 1.0397. Min Range: -1.0397

Max Act: 1.0397. Min Act: -0.0000

Data Index: 491129 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8505. Min Act: -0.0000

Data Index: 66164 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8761. Min Act: -0.0000

Data Index: 602380 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7000. Min Act: -0.0000

Data Index: 298424 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1439438 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.5796. Min Act: -0.0000

Data Index: 852186 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.5648. Min Act: -0.0000

Data Index: 543948 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.5993. Min Act: -0.0000

Data Index: 504811 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.6144. Min Act: -0.0000

Data Index: 667339 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.6441. Min Act: -0.0000

Data Index: 583329 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1962984 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.5207. Min Act: -0.0000

Data Index: 238968 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1597881 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.5243. Min Act: -0.0000

Data Index: 533690 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.5327. Min Act: -0.0000

Data Index: 952825 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1778768 (The Pile)

Max Activating Token Index: 647

Text #17

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1405734 (The Pile)

Max Activating Token Index: 815

Text #18

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1674338 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.4780. Min Act: -0.0000

Data Index: 449398 (The Pile)

Max Activating Token Index: 409