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

Dataset: The Pile

Neuron 3204 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: 1.1513. Min Range: -1.1513

Max Act: 1.1513. Min Act: -0.0000

Data Index: 913277 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 1.1513. Min Range: -1.1513

Max Act: 1.0916. Min Act: -0.0000

Data Index: 390964 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1071353 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1469163 (The Pile)

Max Activating Token Index: 893

Text #4

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1912017 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.7768. Min Act: -0.0000

Data Index: 448023 (The Pile)

Max Activating Token Index: 517

Text #6

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1730762 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.7202. Min Act: -0.0000

Data Index: 555596 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6778. Min Act: -0.0000

Data Index: 955723 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.7126. Min Act: -0.0000

Data Index: 188888 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6884. Min Act: -0.0000

Data Index: 440654 (The Pile)

Max Activating Token Index: 411

Text #11

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1551840 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6862. Min Act: -0.0000

Data Index: 70984 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1321909 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6692. Min Act: -0.0000

Data Index: 638369 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1893645 (The Pile)

Max Activating Token Index: 653

Text #16

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1331441 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1413456 (The Pile)

Max Activating Token Index: 965

Text #18

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1129813 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1138314 (The Pile)

Max Activating Token Index: 1009