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

Dataset: The Pile

Neuron 3249 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.4865. Min Act: -0.0000

Data Index: 121882 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.5563. Min Act: -0.0000

Data Index: 1707290 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1095972 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.4097. Min Act: -0.0000

Data Index: 810635 (The Pile)

Max Activating Token Index: 658

Text #4

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1594943 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.2525. Min Act: -0.0000

Data Index: 602916 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.1862. Min Act: -0.0000

Data Index: 732532 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.1751. Min Act: -0.0000

Data Index: 413267 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.1680. Min Act: -0.0000

Data Index: 1869313 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1376464 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 1.5563. Min Range: -1.5563

Max Act: 0.9953. Min Act: -0.0000

Data Index: 278140 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.1167. Min Act: -0.0000

Data Index: 1364228 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 1.5563. Min Range: -1.5563

Max Act: 0.9860. Min Act: -0.0000

Data Index: 496884 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 1.5563. Min Range: -1.5563

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1775036 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 1.5563. Min Range: -1.5563

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1309350 (The Pile)

Max Activating Token Index: 504

Text #15

Max Range: 1.5563. Min Range: -1.5563

Max Act: 0.9999. Min Act: -0.0000

Data Index: 1050879 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 1.5563. Min Range: -1.5563

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1464840 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 1.5563. Min Range: -1.5563

Max Act: 0.9412. Min Act: -0.0000

Data Index: 517097 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 1.5563. Min Range: -1.5563

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1510299 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 1.5563. Min Range: -1.5563

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1336455 (The Pile)

Max Activating Token Index: 589