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

Dataset: The Pile

Neuron 973 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3821. Min Act: 0.0000

Data Index: 1970133 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1343824 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1723981 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3389. Min Act: -0.0000

Data Index: 150516 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3840. Min Act: 0.0000

Data Index: 1676619 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1731146 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3221. Min Act: -0.0000

Data Index: 664606 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3195. Min Act: 0.0000

Data Index: 952653 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3434. Min Act: -0.0000

Data Index: 840895 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3241. Min Act: -0.0000

Data Index: 633101 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3224. Min Act: -0.0000

Data Index: 464823 (The Pile)

Max Activating Token Index: 435

Text #11

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3403. Min Act: -0.0000

Data Index: 796604 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1770826 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1761003 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3198. Min Act: -0.0000

Data Index: 546237 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2909. Min Act: -0.0000

Data Index: 359669 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2957. Min Act: -0.0000

Data Index: 851345 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1625120 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2762. Min Act: -0.0001

Data Index: 756247 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1469116 (The Pile)

Max Activating Token Index: 336