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

Dataset: The Pile

Neuron 3448 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.4712. Min Act: -0.0000

Data Index: 846867 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.4247. Min Act: -0.0000

Data Index: 79948 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3353. Min Act: -0.0000

Data Index: 1567482 (The Pile)

Max Activating Token Index: 554

Text #3

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.4006. Min Act: -0.0000

Data Index: 1978381 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3498. Min Act: -0.0000

Data Index: 335026 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2690. Min Act: -0.0000

Data Index: 114341 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1596588 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1138560 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.1992. Min Act: -0.0000

Data Index: 588755 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1409075 (The Pile)

Max Activating Token Index: 559

Text #10

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2643. Min Act: -0.0000

Data Index: 356063 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1124099 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2166. Min Act: -0.0000

Data Index: 631568 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2078. Min Act: -0.0000

Data Index: 121395 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.1916. Min Act: -0.0000

Data Index: 609970 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1376131 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.1751. Min Act: -0.0000

Data Index: 1409711 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.1699. Min Act: -0.0000

Data Index: 704399 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.1503. Min Act: -0.0000

Data Index: 398650 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.1492. Min Act: -0.0000

Data Index: 627019 (The Pile)

Max Activating Token Index: 237