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

Dataset: The Pile

Neuron 4486 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: 0.2644. Min Range: -0.2644

Max Act: 0.2644. Min Act: -0.0000

Data Index: 501905 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1753512 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1430430 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2294. Min Act: -0.0000

Data Index: 190188 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1304756 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1596267 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1592115 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1283869 (The Pile)

Max Activating Token Index: 533

Text #8

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2279. Min Act: -0.0000

Data Index: 970130 (The Pile)

Max Activating Token Index: 644

Text #9

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2241. Min Act: -0.0000

Data Index: 95077 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2180. Min Act: -0.0000

Data Index: 224203 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2126. Min Act: -0.0000

Data Index: 61536 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1805277 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2009. Min Act: -0.0000

Data Index: 917675 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2008. Min Act: -0.0000

Data Index: 925577 (The Pile)

Max Activating Token Index: 875

Text #15

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2086. Min Act: -0.0000

Data Index: 734508 (The Pile)

Max Activating Token Index: 295

Text #16

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2050. Min Act: -0.0000

Data Index: 615849 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2022. Min Act: -0.0000

Data Index: 739066 (The Pile)

Max Activating Token Index: 336

Text #18

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1865. Min Act: -0.0000

Data Index: 320943 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2042. Min Act: -0.0000

Data Index: 448258 (The Pile)

Max Activating Token Index: 498