Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1916 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.7678. Min Act: -0.0000

Data Index: 695366 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1573646 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1290589 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1202756 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1981876 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4677. Min Act: -0.0000

Data Index: 423988 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1987329 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1233081 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1543230 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2736. Min Act: -0.0000

Data Index: 409739 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2606. Min Act: -0.0000

Data Index: 755291 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2531. Min Act: -0.0000

Data Index: 89054 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2155. Min Act: -0.0000

Data Index: 756521 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2344. Min Act: -0.0000

Data Index: 172973 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2276. Min Act: -0.0000

Data Index: 1393112 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2414. Min Act: -0.0000

Data Index: 292811 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1599237 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1347141 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1333983 (The Pile)

Max Activating Token Index: 296

Text #19

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1036706 (The Pile)

Max Activating Token Index: 934