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

Dataset: The Pile

Neuron 3047 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: 1.4357. Min Range: -1.4357

Max Act: 1.4164. Min Act: -0.0000

Data Index: 905067 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.4357. Min Act: -0.0000

Data Index: 4051 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1939. Min Act: -0.0000

Data Index: 1994578 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.2517. Min Act: -0.0000

Data Index: 318251 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1926740 (The Pile)

Max Activating Token Index: 616

Text #5

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1349355 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1382071 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1196. Min Act: -0.0000

Data Index: 931658 (The Pile)

Max Activating Token Index: 917

Text #8

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1637798 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1909823 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.0383. Min Act: -0.0000

Data Index: 1432465 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1332015 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.9973. Min Act: -0.0000

Data Index: 500697 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.9284. Min Act: -0.0000

Data Index: 169487 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.9129. Min Act: -0.0000

Data Index: 713236 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.8768. Min Act: -0.0000

Data Index: 971820 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1740891 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.8433. Min Act: -0.0000

Data Index: 727473 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1351519 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.8968. Min Act: -0.0000

Data Index: 220698 (The Pile)

Max Activating Token Index: 393