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

Dataset: The Pile

Neuron 3493 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0809. Min Range: -5.0809

Max Act: 5.0633. Min Act: -0.0000

Data Index: 553911 (The Pile)

Max Activating Token Index: 342

Text #1

Max Range: 5.0809. Min Range: -5.0809

Max Act: 5.0809. Min Act: -0.0000

Data Index: 767114 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.5723. Min Act: -0.0000

Data Index: 25861 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.0039. Min Act: -0.0000

Data Index: 522561 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.1430. Min Act: -0.0000

Data Index: 621069 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.0667. Min Act: -0.0000

Data Index: 1344416 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.0738. Min Act: -0.0000

Data Index: 1402985 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.0743. Min Act: -0.0000

Data Index: 1233826 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.6998. Min Act: -0.0000

Data Index: 522991 (The Pile)

Max Activating Token Index: 634

Text #9

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.7582. Min Act: -0.0000

Data Index: 99503 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.9660. Min Act: -0.0000

Data Index: 198454 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.7123. Min Act: -0.0000

Data Index: 165608 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.6919. Min Act: -0.0000

Data Index: 1924456 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.3107. Min Act: -0.0000

Data Index: 1925828 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.5128. Min Act: -0.0000

Data Index: 910533 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.5602. Min Act: -0.0000

Data Index: 460148 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.5396. Min Act: -0.0000

Data Index: 252794 (The Pile)

Max Activating Token Index: 920

Text #17

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.5278. Min Act: -0.0000

Data Index: 1655249 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.3522. Min Act: -0.0000

Data Index: 1403220 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 5.0809. Min Range: -5.0809

Max Act: 3.4923. Min Act: -0.0000

Data Index: 360572 (The Pile)

Max Activating Token Index: 939