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

Dataset: The Pile

Neuron 3737 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.8334. Min Act: -0.0000

Data Index: 1198015 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.7484. Min Act: -0.0000

Data Index: 1064681 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.7709. Min Act: -0.0000

Data Index: 1579869 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6602. Min Act: -0.0000

Data Index: 1664536 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6989. Min Act: -0.0000

Data Index: 1769400 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6611. Min Act: -0.0000

Data Index: 1249610 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6589. Min Act: -0.0000

Data Index: 1940032 (The Pile)

Max Activating Token Index: 254

Text #7

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1601988 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1878474 (The Pile)

Max Activating Token Index: 683

Text #9

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1848211 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1715181 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6400. Min Act: -0.0000

Data Index: 386256 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5919. Min Act: -0.0000

Data Index: 1336212 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5474. Min Act: -0.0000

Data Index: 1504768 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6274. Min Act: -0.0000

Data Index: 124986 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5766. Min Act: -0.0000

Data Index: 167347 (The Pile)

Max Activating Token Index: 226

Text #16

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6094. Min Act: -0.0000

Data Index: 1279438 (The Pile)

Max Activating Token Index: 402

Text #17

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.6938. Min Act: -0.0000

Data Index: 804570 (The Pile)

Max Activating Token Index: 336

Text #18

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5705. Min Act: -0.0000

Data Index: 1937812 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 1.8334. Min Range: -1.8334

Max Act: 1.5693. Min Act: -0.0000

Data Index: 958100 (The Pile)

Max Activating Token Index: 560