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

Dataset: The Pile

Neuron 3928 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.6124. Min Range: -10.6124

Max Act: 10.6124. Min Act: -0.0000

Data Index: 1909823 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 10.6124. Min Range: -10.6124

Max Act: 6.8433. Min Act: -0.0000

Data Index: 76022 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 10.6124. Min Range: -10.6124

Max Act: 7.8246. Min Act: -0.0000

Data Index: 722666 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 10.6124. Min Range: -10.6124

Max Act: 7.6597. Min Act: -0.0000

Data Index: 1625045 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 10.6124. Min Range: -10.6124

Max Act: 6.6750. Min Act: -0.0000

Data Index: 1636466 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 10.6124. Min Range: -10.6124

Max Act: 7.5316. Min Act: -0.0000

Data Index: 1566608 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 10.6124. Min Range: -10.6124

Max Act: 6.8931. Min Act: -0.0000

Data Index: 1478505 (The Pile)

Max Activating Token Index: 894

Text #7

Max Range: 10.6124. Min Range: -10.6124

Max Act: 6.3767. Min Act: -0.0000

Data Index: 1595355 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 10.6124. Min Range: -10.6124

Max Act: 7.2215. Min Act: -0.0000

Data Index: 1085815 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 10.6124. Min Range: -10.6124

Max Act: 6.4898. Min Act: -0.0000

Data Index: 726370 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 10.6124. Min Range: -10.6124

Max Act: 6.4190. Min Act: -0.0000

Data Index: 1784804 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 10.6124. Min Range: -10.6124

Max Act: 6.7632. Min Act: -0.0000

Data Index: 1137041 (The Pile)

Max Activating Token Index: 439

Text #12

Max Range: 10.6124. Min Range: -10.6124

Max Act: 7.1011. Min Act: -0.0000

Data Index: 1491907 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 10.6124. Min Range: -10.6124

Max Act: 6.5143. Min Act: -0.0000

Data Index: 1998553 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 10.6124. Min Range: -10.6124

Max Act: 5.5596. Min Act: -0.0000

Data Index: 1976885 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 10.6124. Min Range: -10.6124

Max Act: 5.8275. Min Act: -0.0000

Data Index: 1036127 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 10.6124. Min Range: -10.6124

Max Act: 6.3176. Min Act: -0.0000

Data Index: 1760424 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 10.6124. Min Range: -10.6124

Max Act: 5.3011. Min Act: -0.0000

Data Index: 1698423 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 10.6124. Min Range: -10.6124

Max Act: 5.9359. Min Act: -0.0000

Data Index: 1325298 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 10.6124. Min Range: -10.6124

Max Act: 5.7681. Min Act: -0.0000

Data Index: 1642479 (The Pile)

Max Activating Token Index: 638