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

Dataset: The Pile

Neuron 4439 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: 0.0000

Data Index: 1877773 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0347. Min Act: -0.0000

Data Index: 118449 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1346129 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0346. Min Act: -0.0000

Data Index: 352868 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0338. Min Act: 0.0000

Data Index: 722290 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0337. Min Act: 0.0000

Data Index: 579373 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0336. Min Act: 0.0000

Data Index: 94597 (The Pile)

Max Activating Token Index: 35

Text #7

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1530746 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0322. Min Act: -0.0000

Data Index: 803749 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1716460 (The Pile)

Max Activating Token Index: 6

Text #10

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0322. Min Act: 0.0000

Data Index: 1263101 (The Pile)

Max Activating Token Index: 6

Text #11

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0332. Min Act: -0.0000

Data Index: 1438412 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0329. Min Act: -0.0000

Data Index: 874317 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0328. Min Act: 0.0000

Data Index: 1411877 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0328. Min Act: -0.0000

Data Index: 439323 (The Pile)

Max Activating Token Index: 6

Text #15

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0328. Min Act: 0.0000

Data Index: 1116246 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1507297 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0328. Min Act: -0.0000

Data Index: 354256 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0326. Min Act: -0.0000

Data Index: 418629 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0326. Min Act: -0.0000

Data Index: 53916 (The Pile)

Max Activating Token Index: 35