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

Dataset: The Pile

Neuron 448 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1384997 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0798. Min Act: -0.0000

Data Index: 342133 (The Pile)

Max Activating Token Index: 844

Text #2

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0726. Min Act: -0.0000

Data Index: 409794 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0680. Min Act: -0.0000

Data Index: 369167 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0682. Min Act: -0.0000

Data Index: 460876 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1796360 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1521697 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1493000 (The Pile)

Max Activating Token Index: 671

Text #8

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1147917 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0600. Min Act: -0.0000

Data Index: 529951 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0605. Min Act: -0.0000

Data Index: 727922 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0591. Min Act: -0.0000

Data Index: 591715 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1446092 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1310523 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1664343 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0629. Min Act: -0.0000

Data Index: 424135 (The Pile)

Max Activating Token Index: 923

Text #16

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0581. Min Act: -0.0000

Data Index: 173913 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1337437 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0530. Min Act: -0.0000

Data Index: 17916 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0544. Min Act: -0.0000

Data Index: 191096 (The Pile)

Max Activating Token Index: 135