Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.2579. Min Act: -0.0000

Data Index: 502932 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.2415. Min Act: 0.0000

Data Index: 1140908 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1465. Min Act: 0.0001

Data Index: 251059 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1693. Min Act: 0.0000

Data Index: 728032 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1863555 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9495. Min Act: -0.0000

Data Index: 260226 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0801. Min Act: -0.0000

Data Index: 1673766 (The Pile)

Max Activating Token Index: 688

Text #7

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1845501 (The Pile)

Max Activating Token Index: 48

Text #8

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1134065 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9000. Min Act: 0.0000

Data Index: 1014183 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1035349 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1750470 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1595437 (The Pile)

Max Activating Token Index: 618

Text #13

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1056291 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9548. Min Act: 0.0000

Data Index: 1947748 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1534831 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9435. Min Act: -0.0000

Data Index: 97975 (The Pile)

Max Activating Token Index: 289

Text #17

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9495. Min Act: -0.0000

Data Index: 218519 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8953. Min Act: -0.0000

Data Index: 87550 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8832. Min Act: -0.0000

Data Index: 73736 (The Pile)

Max Activating Token Index: 237