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

Dataset: The Pile

Neuron 3285 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4372. Min Range: -1.4372

Max Act: 1.4372. Min Act: -0.0000

Data Index: 341841 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 1.4372. Min Range: -1.4372

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1710664 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 1.4372. Min Range: -1.4372

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1757639 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 1.4372. Min Range: -1.4372

Max Act: 1.1603. Min Act: -0.0000

Data Index: 1429515 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 1.4372. Min Range: -1.4372

Max Act: 1.0342. Min Act: -0.0000

Data Index: 608701 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1861554 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1897538 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.9841. Min Act: -0.0000

Data Index: 973944 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1216881 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1747789 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.9397. Min Act: -0.0000

Data Index: 285847 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1079673 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.9229. Min Act: -0.0000

Data Index: 813298 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.8511. Min Act: -0.0000

Data Index: 209560 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1982714 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1101927 (The Pile)

Max Activating Token Index: 356

Text #16

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.7757. Min Act: -0.0000

Data Index: 527411 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.9672. Min Act: -0.0000

Data Index: 765326 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.9653. Min Act: -0.0000

Data Index: 312790 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 1.4372. Min Range: -1.4372

Max Act: 0.7585. Min Act: -0.0000

Data Index: 1743082 (The Pile)

Max Activating Token Index: 646