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

Dataset: The Pile

Neuron 3386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0502. Min Range: -1.0502

Max Act: 1.0293. Min Act: -0.0000

Data Index: 788856 (The Pile)

Max Activating Token Index: 886

Text #1

Max Range: 1.0502. Min Range: -1.0502

Max Act: 1.0502. Min Act: -0.0000

Data Index: 220550 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 1.0502. Min Range: -1.0502

Max Act: 1.0158. Min Act: -0.0000

Data Index: 1980120 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 1.0502. Min Range: -1.0502

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1270894 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9544. Min Act: -0.0000

Data Index: 186799 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1563750 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9660. Min Act: -0.0000

Data Index: 24586 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1993161 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9746. Min Act: -0.0000

Data Index: 822674 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9656. Min Act: -0.0000

Data Index: 376148 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1746789 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9907. Min Act: -0.0000

Data Index: 447052 (The Pile)

Max Activating Token Index: 790

Text #12

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8963. Min Act: -0.0000

Data Index: 953753 (The Pile)

Max Activating Token Index: 353

Text #13

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1560891 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1410076 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8992. Min Act: -0.0000

Data Index: 707518 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9259. Min Act: -0.0000

Data Index: 647154 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8364. Min Act: -0.0000

Data Index: 589357 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1946583 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1580462 (The Pile)

Max Activating Token Index: 487