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

Dataset: The Pile

Neuron 3428 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1959348 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1655145 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.5910. Min Act: -0.0000

Data Index: 953589 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.5881. Min Act: 0.0000

Data Index: 498095 (The Pile)

Max Activating Token Index: 464

Text #4

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.5664. Min Act: 0.0000

Data Index: 1221271 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1744891 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.5201. Min Act: -0.0000

Data Index: 513762 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1418371 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.5385. Min Act: 0.0000

Data Index: 1967932 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1410633 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1596805 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1333744 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4583. Min Act: 0.0000

Data Index: 304280 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4788. Min Act: -0.0000

Data Index: 343948 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4406. Min Act: -0.0000

Data Index: 845777 (The Pile)

Max Activating Token Index: 904

Text #15

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1977588 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4373. Min Act: -0.0000

Data Index: 122214 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4390. Min Act: 0.0000

Data Index: 1992058 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1350213 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 0.6669. Min Range: -0.6669

Max Act: 0.4357. Min Act: -0.0000

Data Index: 609647 (The Pile)

Max Activating Token Index: 865