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

Dataset: The Pile

Neuron 2228 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1644507 (The Pile)

Max Activating Token Index: 965

Text #1

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1722660 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1126874 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7313. Min Act: -0.0000

Data Index: 983692 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1658828 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1329372 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5899. Min Act: -0.0000

Data Index: 245386 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1369587 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6208. Min Act: 0.0000

Data Index: 1523826 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6034. Min Act: -0.0000

Data Index: 827003 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1974001 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5765. Min Act: 0.0000

Data Index: 1200051 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1096552 (The Pile)

Max Activating Token Index: 736

Text #13

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5895. Min Act: -0.0000

Data Index: 117239 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1070500 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5499. Min Act: -0.0000

Data Index: 744365 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1559610 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5770. Min Act: -0.0000

Data Index: 541459 (The Pile)

Max Activating Token Index: 431

Text #18

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5516. Min Act: -0.0000

Data Index: 658619 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5475. Min Act: -0.0000

Data Index: 524216 (The Pile)

Max Activating Token Index: 106