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

Dataset: The Pile

Neuron 3575 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: 2.1631. Min Range: -2.1631

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1849628 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 2.1631. Min Range: -2.1631

Max Act: 2.1631. Min Act: -0.0000

Data Index: 1629816 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 2.1631. Min Range: -2.1631

Max Act: 2.0043. Min Act: -0.0000

Data Index: 1905185 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.9233. Min Act: -0.0000

Data Index: 218292 (The Pile)

Max Activating Token Index: 564

Text #4

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.9396. Min Act: -0.0000

Data Index: 1352743 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.9246. Min Act: -0.0000

Data Index: 931790 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7312. Min Act: -0.0000

Data Index: 1714626 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7954. Min Act: -0.0000

Data Index: 270361 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.8049. Min Act: -0.0000

Data Index: 1521740 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7995. Min Act: -0.0000

Data Index: 1411423 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7869. Min Act: -0.0000

Data Index: 1618820 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.6884. Min Act: -0.0000

Data Index: 1990427 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.6834. Min Act: -0.0000

Data Index: 621672 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.6644. Min Act: -0.0000

Data Index: 1540948 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.8808. Min Act: -0.0000

Data Index: 1247508 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.8433. Min Act: -0.0000

Data Index: 475531 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.6454. Min Act: -0.0000

Data Index: 666814 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7362. Min Act: -0.0000

Data Index: 1349396 (The Pile)

Max Activating Token Index: 472

Text #18

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7458. Min Act: -0.0000

Data Index: 1273938 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.6605. Min Act: -0.0000

Data Index: 604144 (The Pile)

Max Activating Token Index: 953