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

Dataset: The Pile

Neuron 3453 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3895. Min Act: -0.0000

Data Index: 821670 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1556738 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2750. Min Act: -0.0000

Data Index: 717736 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2679. Min Act: -0.0000

Data Index: 416344 (The Pile)

Max Activating Token Index: 299

Text #4

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2708. Min Act: -0.0000

Data Index: 293664 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2696. Min Act: -0.0000

Data Index: 721013 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2613. Min Act: -0.0000

Data Index: 910308 (The Pile)

Max Activating Token Index: 608

Text #7

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2406. Min Act: -0.0000

Data Index: 696817 (The Pile)

Max Activating Token Index: 739

Text #8

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2450. Min Act: -0.0000

Data Index: 95225 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1977996 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2507. Min Act: -0.0000

Data Index: 94535 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1646772 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2460. Min Act: -0.0000

Data Index: 682193 (The Pile)

Max Activating Token Index: 873

Text #13

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1515254 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2401. Min Act: -0.0000

Data Index: 782391 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2284. Min Act: -0.0000

Data Index: 927019 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2403. Min Act: -0.0000

Data Index: 992591 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2284. Min Act: -0.0000

Data Index: 179459 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2278. Min Act: -0.0000

Data Index: 288564 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1273013 (The Pile)

Max Activating Token Index: 533