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

Dataset: The Pile

Neuron 470 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: 1.0232. Min Range: -1.0232

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1409966 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.9868. Min Act: -0.0000

Data Index: 288152 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1567869 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1016780 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1796020 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1088839 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8977. Min Act: -0.0000

Data Index: 691077 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8199. Min Act: -0.0000

Data Index: 755127 (The Pile)

Max Activating Token Index: 585

Text #8

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8726. Min Act: -0.0000

Data Index: 838848 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8677. Min Act: -0.0000

Data Index: 868286 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8720. Min Act: -0.0000

Data Index: 23881 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8667. Min Act: -0.0000

Data Index: 698770 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1864195 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.9105. Min Act: -0.0000

Data Index: 978740 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1523684 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1335927 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7678. Min Act: -0.0000

Data Index: 706953 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1584198 (The Pile)

Max Activating Token Index: 882

Text #18

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7831. Min Act: -0.0000

Data Index: 804795 (The Pile)

Max Activating Token Index: 298

Text #19

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1647836 (The Pile)

Max Activating Token Index: 630