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

Dataset: The Pile

Neuron 5077 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: 0.7983. Min Range: -0.7983

Max Act: 0.7983. Min Act: -0.0000

Data Index: 123154 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1971915 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1321211 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7415. Min Act: -0.0000

Data Index: 104593 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1505446 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1869219 (The Pile)

Max Activating Token Index: 39

Text #6

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1137078 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1672188 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1965348 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6676. Min Act: -0.0000

Data Index: 962077 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6127. Min Act: -0.0000

Data Index: 824624 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6200. Min Act: -0.0000

Data Index: 570823 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6377. Min Act: -0.0000

Data Index: 746724 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6339. Min Act: -0.0000

Data Index: 705909 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6131. Min Act: -0.0000

Data Index: 984240 (The Pile)

Max Activating Token Index: 856

Text #15

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5889. Min Act: -0.0000

Data Index: 764749 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5984. Min Act: -0.0000

Data Index: 872911 (The Pile)

Max Activating Token Index: 796

Text #17

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1627163 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1060876 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1867428 (The Pile)

Max Activating Token Index: 499