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

Dataset: The Pile

Neuron 4635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0418. Min Range: -1.0418

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1661475 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1371726 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.9903. Min Act: -0.0000

Data Index: 987979 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.9074. Min Act: -0.0000

Data Index: 437684 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8979. Min Act: -0.0000

Data Index: 61312 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1531018 (The Pile)

Max Activating Token Index: 892

Text #6

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1258340 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8652. Min Act: -0.0000

Data Index: 536697 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1858784 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1892328 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1722495 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1861561 (The Pile)

Max Activating Token Index: 771

Text #12

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8377. Min Act: -0.0000

Data Index: 597263 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.9161. Min Act: -0.0000

Data Index: 130886 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1941518 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1752000 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.9079. Min Act: -0.0000

Data Index: 147224 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8107. Min Act: -0.0000

Data Index: 516440 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8385. Min Act: -0.0000

Data Index: 763958 (The Pile)

Max Activating Token Index: 405

Text #19

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1155371 (The Pile)

Max Activating Token Index: 529