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

Dataset: The Pile

Neuron 2896 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: 1.3529. Min Range: -1.3529

Max Act: 1.2891. Min Act: -0.0000

Data Index: 293978 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.2426. Min Act: -0.0000

Data Index: 816207 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1492344 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.2165. Min Act: -0.0000

Data Index: 513220 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1119452 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1663811 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.2092. Min Act: -0.0000

Data Index: 688035 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1328. Min Act: -0.0000

Data Index: 1042632 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1494349 (The Pile)

Max Activating Token Index: 394

Text #9

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1063338 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1213966 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1747801 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1769. Min Act: -0.0000

Data Index: 1836234 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1233935 (The Pile)

Max Activating Token Index: 720

Text #14

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1845. Min Act: -0.0000

Data Index: 571050 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1409. Min Act: -0.0000

Data Index: 797682 (The Pile)

Max Activating Token Index: 210

Text #16

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1962537 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.0823. Min Act: -0.0000

Data Index: 282496 (The Pile)

Max Activating Token Index: 472

Text #18

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1996365 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1709766 (The Pile)

Max Activating Token Index: 426