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

Dataset: The Pile

Neuron 3697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1742145 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.4605. Min Act: -0.0000

Data Index: 246283 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.2307. Min Act: -0.0000

Data Index: 171626 (The Pile)

Max Activating Token Index: 74

Text #3

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1220884 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1086805 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1694496 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1902082 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9442. Min Act: -0.0000

Data Index: 600658 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1646156 (The Pile)

Max Activating Token Index: 748

Text #9

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1493899 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1246085 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1953724 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1106361 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.8831. Min Act: -0.0000

Data Index: 953289 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.8986. Min Act: -0.0000

Data Index: 391353 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.8602. Min Act: -0.0000

Data Index: 349927 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1267973 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1544872 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.8367. Min Act: -0.0000

Data Index: 744308 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1530387 (The Pile)

Max Activating Token Index: 815