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

Dataset: The Pile

Neuron 4307 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1330. Min Range: -1.1330

Max Act: 1.1330. Min Act: 0.0001

Data Index: 1674519 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 1.1330. Min Range: -1.1330

Max Act: 1.0031. Min Act: -0.0000

Data Index: 376582 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9669. Min Act: -0.0000

Data Index: 176364 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9573. Min Act: 0.0000

Data Index: 1168879 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9020. Min Act: 0.0000

Data Index: 1958442 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1995445 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1388311 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8315. Min Act: -0.0000

Data Index: 729488 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1891298 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8069. Min Act: -0.0000

Data Index: 867095 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1106990 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8007. Min Act: 0.0000

Data Index: 476987 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.7954. Min Act: -0.0000

Data Index: 817980 (The Pile)

Max Activating Token Index: 37

Text #13

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.7722. Min Act: -0.0000

Data Index: 991433 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1831820 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1651472 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.7837. Min Act: 0.0000

Data Index: 1489321 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.7704. Min Act: -0.0000

Data Index: 817535 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1655687 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1595037 (The Pile)

Max Activating Token Index: 225