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

Dataset: The Pile

Neuron 4851 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: 3.5440. Min Range: -3.5440

Max Act: 3.4249. Min Act: -0.0000

Data Index: 460148 (The Pile)

Max Activating Token Index: 873

Text #1

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.5440. Min Act: -0.0000

Data Index: 1606448 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2398. Min Act: -0.0000

Data Index: 1621921 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2053. Min Act: -0.0000

Data Index: 1896191 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2090. Min Act: -0.0000

Data Index: 113208 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.3134. Min Act: -0.0000

Data Index: 273803 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.0459. Min Act: -0.0000

Data Index: 1994523 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.1611. Min Act: -0.0000

Data Index: 811116 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2943. Min Act: -0.0000

Data Index: 1262204 (The Pile)

Max Activating Token Index: 992

Text #9

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.0017. Min Act: -0.0000

Data Index: 1591654 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.1474. Min Act: -0.0000

Data Index: 1768612 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2401. Min Act: -0.0000

Data Index: 647433 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.1224. Min Act: -0.0000

Data Index: 452146 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.0995. Min Act: -0.0000

Data Index: 1255974 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2511. Min Act: -0.0000

Data Index: 1487682 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.0980. Min Act: -0.0000

Data Index: 1228410 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.0743. Min Act: -0.0000

Data Index: 1728428 (The Pile)

Max Activating Token Index: 4

Text #17

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.0892. Min Act: -0.0000

Data Index: 919444 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.0625. Min Act: -0.0000

Data Index: 1867056 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.0483. Min Act: -0.0000

Data Index: 261267 (The Pile)

Max Activating Token Index: 319