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

Dataset: The Pile

Neuron 469 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: 0.9979. Min Range: -0.9979

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1938754 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1902581 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1587703 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.9468. Min Act: -0.0000

Data Index: 265002 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1520134 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.9979. Min Act: -0.0000

Data Index: 406941 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1393413 (The Pile)

Max Activating Token Index: 744

Text #7

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8446. Min Act: -0.0000

Data Index: 748498 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8651. Min Act: -0.0000

Data Index: 487971 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1854204 (The Pile)

Max Activating Token Index: 870

Text #10

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1475966 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1504078 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8313. Min Act: -0.0000

Data Index: 106624 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7953. Min Act: -0.0000

Data Index: 145029 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1565089 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1527151 (The Pile)

Max Activating Token Index: 473

Text #16

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1254149 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1847094 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1638491 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1747267 (The Pile)

Max Activating Token Index: 889