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

Dataset: The Pile

Neuron 3890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1644337 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5662. Min Act: -0.0000

Data Index: 672930 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5853. Min Act: -0.0000

Data Index: 293404 (The Pile)

Max Activating Token Index: 688

Text #3

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5824. Min Act: -0.0000

Data Index: 141764 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5432. Min Act: -0.0000

Data Index: 679811 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1104357 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5431. Min Act: -0.0000

Data Index: 694415 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1357871 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5399. Min Act: -0.0000

Data Index: 669101 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1731718 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5561. Min Act: -0.0000

Data Index: 885636 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5194. Min Act: -0.0000

Data Index: 457882 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1900211 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1821171 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4932. Min Act: -0.0001

Data Index: 1906890 (The Pile)

Max Activating Token Index: 188

Text #15

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1223103 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1947338 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4676. Min Act: -0.0000

Data Index: 185744 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1282281 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1391126 (The Pile)

Max Activating Token Index: 125