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

Dataset: The Pile

Neuron 3535 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: 3.1889. Min Range: -3.1889

Max Act: 3.1889. Min Act: -0.0000

Data Index: 1991090 (The Pile)

Max Activating Token Index: 838

Text #1

Max Range: 3.1889. Min Range: -3.1889

Max Act: 2.6365. Min Act: -0.0000

Data Index: 126309 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 3.1889. Min Range: -3.1889

Max Act: 2.1001. Min Act: -0.0000

Data Index: 163651 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 3.1889. Min Range: -3.1889

Max Act: 2.1742. Min Act: -0.0000

Data Index: 842807 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.9217. Min Act: -0.0000

Data Index: 310656 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 3.1889. Min Range: -3.1889

Max Act: 2.0012. Min Act: -0.0000

Data Index: 43427 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 3.1889. Min Range: -3.1889

Max Act: 2.0547. Min Act: -0.0000

Data Index: 99290 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.8690. Min Act: -0.0000

Data Index: 1898289 (The Pile)

Max Activating Token Index: 404

Text #8

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.8645. Min Act: -0.0000

Data Index: 71148 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.7302. Min Act: -0.0000

Data Index: 524772 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.7722. Min Act: -0.0000

Data Index: 528121 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.6378. Min Act: -0.0000

Data Index: 1056314 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.5337. Min Act: -0.0000

Data Index: 406867 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.4290. Min Act: -0.0000

Data Index: 318674 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.3414. Min Act: -0.0000

Data Index: 394256 (The Pile)

Max Activating Token Index: 804

Text #15

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.4468. Min Act: -0.0000

Data Index: 289042 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.2682. Min Act: -0.0000

Data Index: 944473 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.2416. Min Act: -0.0000

Data Index: 1013310 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1316371 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 3.1889. Min Range: -3.1889

Max Act: 1.3957. Min Act: -0.0000

Data Index: 1561677 (The Pile)

Max Activating Token Index: 932