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

Dataset: The Pile

Neuron 2823 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2484. Min Range: -1.2484

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1591495 (The Pile)

Max Activating Token Index: 216

Text #1

Max Range: 1.2484. Min Range: -1.2484

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1026348 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 1.2484. Min Range: -1.2484

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1530603 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 1.2484. Min Range: -1.2484

Max Act: 1.0621. Min Act: -0.0000

Data Index: 535726 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 1.2484. Min Range: -1.2484

Max Act: 1.1220. Min Act: -0.0000

Data Index: 530696 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 1.2484. Min Range: -1.2484

Max Act: 1.1569. Min Act: -0.0000

Data Index: 621238 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 1.2484. Min Range: -1.2484

Max Act: 1.0867. Min Act: -0.0000

Data Index: 209391 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 1.2484. Min Range: -1.2484

Max Act: 1.0266. Min Act: -0.0000

Data Index: 320122 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1533224 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 1.2484. Min Range: -1.2484

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1807477 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1863505 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.9679. Min Act: -0.0000

Data Index: 357744 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1281541 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1379663 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.9581. Min Act: -0.0000

Data Index: 719853 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.9515. Min Act: -0.0000

Data Index: 73798 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.9398. Min Act: -0.0000

Data Index: 552845 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.9832. Min Act: -0.0000

Data Index: 190825 (The Pile)

Max Activating Token Index: 858

Text #18

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.8659. Min Act: -0.0000

Data Index: 158277 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 1.2484. Min Range: -1.2484

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1687119 (The Pile)

Max Activating Token Index: 119