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

Dataset: The Pile

Neuron 414 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.1619. Min Act: -0.0000

Data Index: 223731 (The Pile)

Max Activating Token Index: 748

Text #1

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0193. Min Act: 0.0000

Data Index: 1432929 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0298. Min Act: -0.0000

Data Index: 430871 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1610357 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9750. Min Act: 0.0000

Data Index: 500310 (The Pile)

Max Activating Token Index: 411

Text #5

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9971. Min Act: 0.0000

Data Index: 1575803 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9907. Min Act: 0.0000

Data Index: 1944949 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1950122 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9650. Min Act: 0.0000

Data Index: 1970950 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1286716 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1242877 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9386. Min Act: -0.0000

Data Index: 808810 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8425. Min Act: -0.0000

Data Index: 511004 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9046. Min Act: -0.0000

Data Index: 300104 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8282. Min Act: 0.0000

Data Index: 166425 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1815261 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8782. Min Act: 0.0000

Data Index: 579300 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8746. Min Act: -0.0000

Data Index: 335137 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1302214 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8046. Min Act: -0.0000

Data Index: 661941 (The Pile)

Max Activating Token Index: 177