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

Dataset: The Pile

Neuron 4541 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: 1.7180. Min Range: -1.7180

Max Act: 1.7180. Min Act: -0.0000

Data Index: 820589 (The Pile)

Max Activating Token Index: 869

Text #1

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1005621 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1508329 (The Pile)

Max Activating Token Index: 954

Text #3

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1591037 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.1725. Min Act: -0.0000

Data Index: 1650167 (The Pile)

Max Activating Token Index: 819

Text #5

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.0314. Min Act: 0.0000

Data Index: 1542681 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.0310. Min Act: -0.0000

Data Index: 197570 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 1.7180. Min Range: -1.7180

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1016519 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1548439 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.0658. Min Act: -0.0000

Data Index: 793338 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 1.7180. Min Range: -1.7180

Max Act: 0.9783. Min Act: -0.0000

Data Index: 300439 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.0144. Min Act: -0.0000

Data Index: 116615 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.0428. Min Act: -0.0000

Data Index: 671333 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 1.7180. Min Range: -1.7180

Max Act: 0.9908. Min Act: -0.0000

Data Index: 605546 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 1.7180. Min Range: -1.7180

Max Act: 0.9301. Min Act: 0.0000

Data Index: 1130344 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 1.7180. Min Range: -1.7180

Max Act: 0.9353. Min Act: -0.0000

Data Index: 389553 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 1.7180. Min Range: -1.7180

Max Act: 0.9544. Min Act: -0.0000

Data Index: 512063 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 1.7180. Min Range: -1.7180

Max Act: 0.9499. Min Act: 0.0000

Data Index: 912861 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.7180. Min Range: -1.7180

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1162580 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.7180. Min Range: -1.7180

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1996692 (The Pile)

Max Activating Token Index: 699