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

Dataset: The Pile

Neuron 1206 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1392820 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1808001 (The Pile)

Max Activating Token Index: 483

Text #2

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1556. Min Act: -0.0000

Data Index: 941892 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1802. Min Act: -0.0000

Data Index: 880034 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1642. Min Act: -0.0000

Data Index: 618567 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1666. Min Act: -0.0000

Data Index: 202959 (The Pile)

Max Activating Token Index: 312

Text #6

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1607. Min Act: -0.0000

Data Index: 214892 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1549. Min Act: -0.0000

Data Index: 329562 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1527581 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1557880 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1536. Min Act: -0.0000

Data Index: 551930 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1002583 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1446. Min Act: -0.0000

Data Index: 880318 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1500160 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1207. Min Act: -0.0000

Data Index: 294204 (The Pile)

Max Activating Token Index: 888

Text #15

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1308516 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1185011 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1453. Min Act: -0.0000

Data Index: 246462 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1390. Min Act: -0.0000

Data Index: 646428 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1301. Min Act: -0.0000

Data Index: 48832 (The Pile)

Max Activating Token Index: 625