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

Dataset: The Pile

Neuron 2601 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: 1.9427. Min Range: -1.9427

Max Act: 1.9427. Min Act: -0.0000

Data Index: 1647730 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1115193 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.2878. Min Act: -0.0000

Data Index: 1884258 (The Pile)

Max Activating Token Index: 732

Text #3

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.0623. Min Act: -0.0000

Data Index: 774508 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1520166 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1102055 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1406626 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1587686 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.0448. Min Act: -0.0000

Data Index: 249737 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1473982 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1283992 (The Pile)

Max Activating Token Index: 702

Text #11

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1246945 (The Pile)

Max Activating Token Index: 474

Text #12

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1729672 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1462141 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.8967. Min Act: -0.0000

Data Index: 915878 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1824006 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1923089 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1711564 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.8945. Min Act: -0.0000

Data Index: 962575 (The Pile)

Max Activating Token Index: 830

Text #19

Max Range: 1.9427. Min Range: -1.9427

Max Act: 0.8390. Min Act: -0.0000

Data Index: 783450 (The Pile)

Max Activating Token Index: 552