Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 783 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1619296 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1518227 (The Pile)

Max Activating Token Index: 913

Text #2

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1802375 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1012349 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1821859 (The Pile)

Max Activating Token Index: 178

Text #5

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2213. Min Act: -0.0000

Data Index: 435982 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2209. Min Act: -0.0000

Data Index: 706756 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2292. Min Act: -0.0000

Data Index: 29450 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1155095 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1119793 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2223. Min Act: -0.0000

Data Index: 292747 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1739063 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1960991 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1412923 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2150. Min Act: -0.0001

Data Index: 1681013 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2108. Min Act: -0.0000

Data Index: 510477 (The Pile)

Max Activating Token Index: 652

Text #16

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1215523 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1175109 (The Pile)

Max Activating Token Index: 589

Text #18

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1914. Min Act: -0.0000

Data Index: 330834 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2038. Min Act: -0.0001

Data Index: 688779 (The Pile)

Max Activating Token Index: 468