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

Dataset: The Pile

Neuron 1584 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: 1.2828. Min Range: -1.2828

Max Act: 1.2828. Min Act: -0.0000

Data Index: 1411242 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1671171 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1746969 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.6922. Min Act: -0.0000

Data Index: 445640 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1681419 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.6359. Min Act: -0.0000

Data Index: 383584 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1323714 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.6295. Min Act: -0.0000

Data Index: 451233 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.6042. Min Act: -0.0000

Data Index: 297946 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.6856. Min Act: -0.0000

Data Index: 298641 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.6708. Min Act: -0.0000

Data Index: 10555 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.6451. Min Act: -0.0000

Data Index: 987563 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.5910. Min Act: -0.0000

Data Index: 779415 (The Pile)

Max Activating Token Index: 887

Text #13

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.5214. Min Act: -0.0000

Data Index: 526333 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1500996 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.4924. Min Act: -0.0000

Data Index: 550146 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1887982 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1119512 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1763018 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 1.2828. Min Range: -1.2828

Max Act: 0.5146. Min Act: -0.0000

Data Index: 217246 (The Pile)

Max Activating Token Index: 347