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

Dataset: The Pile

Neuron 4641 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8977. Min Act: -0.0000

Data Index: 1027758 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4200. Min Act: -0.0000

Data Index: 1465563 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0787. Min Act: -0.0000

Data Index: 900417 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0915. Min Act: -0.0000

Data Index: 428089 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0670. Min Act: -0.0000

Data Index: 31452 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1033645 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2093. Min Act: -0.0000

Data Index: 1270678 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0333. Min Act: -0.0000

Data Index: 1986204 (The Pile)

Max Activating Token Index: 941

Text #8

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0775. Min Act: -0.0000

Data Index: 180695 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0622. Min Act: -0.0001

Data Index: 1630298 (The Pile)

Max Activating Token Index: 114

Text #10

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.1066. Min Act: -0.0000

Data Index: 964250 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0291. Min Act: -0.0000

Data Index: 908788 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 1.8977. Min Range: -1.8977

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1200206 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0161. Min Act: -0.0000

Data Index: 383523 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.1290. Min Act: -0.0000

Data Index: 639940 (The Pile)

Max Activating Token Index: 795

Text #15

Max Range: 1.8977. Min Range: -1.8977

Max Act: 0.9143. Min Act: -0.0000

Data Index: 764823 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 1.8977. Min Range: -1.8977

Max Act: 0.9096. Min Act: -0.0000

Data Index: 151304 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1280988 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 1.8977. Min Range: -1.8977

Max Act: 0.9167. Min Act: -0.0000

Data Index: 68732 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 1.8977. Min Range: -1.8977

Max Act: 0.9794. Min Act: -0.0001

Data Index: 161490 (The Pile)

Max Activating Token Index: 5