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

Dataset: The Pile

Neuron 1573 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: 0.6594. Min Range: -0.6594

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1905953 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.6133. Min Act: 0.0000

Data Index: 518223 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.6147. Min Act: -0.0000

Data Index: 259616 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5905. Min Act: 0.0000

Data Index: 101730 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1538108 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1816152 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1558246 (The Pile)

Max Activating Token Index: 274

Text #7

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5197. Min Act: 0.0000

Data Index: 1867840 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1315313 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5294. Min Act: -0.0000

Data Index: 290075 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5089. Min Act: -0.0000

Data Index: 844990 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1642059 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4857. Min Act: 0.0000

Data Index: 1016988 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4675. Min Act: 0.0000

Data Index: 1563981 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5113. Min Act: -0.0000

Data Index: 87255 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4941. Min Act: 0.0000

Data Index: 792500 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1084723 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1886972 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4568. Min Act: -0.0000

Data Index: 551089 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4975. Min Act: 0.0000

Data Index: 1521724 (The Pile)

Max Activating Token Index: 118