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

Dataset: The Pile

Neuron 1590 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: 3.3754. Min Range: -3.3754

Max Act: 3.3754. Min Act: -0.0000

Data Index: 1098312 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.8622. Min Act: -0.0000

Data Index: 1490431 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.7768. Min Act: -0.0000

Data Index: 1821633 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.7309. Min Act: 0.0000

Data Index: 1331015 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.6760. Min Act: -0.0000

Data Index: 819860 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.5788. Min Act: -0.0000

Data Index: 630057 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.4218. Min Act: -0.0000

Data Index: 1178965 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.2046. Min Act: -0.0000

Data Index: 1718556 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.3565. Min Act: -0.0000

Data Index: 938266 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.1542. Min Act: -0.0000

Data Index: 213360 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.1719. Min Act: -0.0000

Data Index: 1098629 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.0911. Min Act: -0.0000

Data Index: 19501 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.3214. Min Act: -0.0000

Data Index: 435457 (The Pile)

Max Activating Token Index: 354

Text #13

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.2714. Min Act: -0.0000

Data Index: 1804954 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.1294. Min Act: -0.0000

Data Index: 1882006 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.1151. Min Act: -0.0000

Data Index: 130461 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.1438. Min Act: -0.0000

Data Index: 1889329 (The Pile)

Max Activating Token Index: 331

Text #17

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.0988. Min Act: -0.0000

Data Index: 349310 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.0896. Min Act: -0.0000

Data Index: 260661 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 3.3754. Min Range: -3.3754

Max Act: 2.3472. Min Act: 0.0001

Data Index: 1478371 (The Pile)

Max Activating Token Index: 986