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

Dataset: The Pile

Neuron 3317 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1327. Min Act: -0.0000

Data Index: 551044 (The Pile)

Max Activating Token Index: 74

Text #1

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1159. Min Act: -0.0000

Data Index: 932893 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1151836 (The Pile)

Max Activating Token Index: 148

Text #3

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1857676 (The Pile)

Max Activating Token Index: 748

Text #4

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1206. Min Act: -0.0000

Data Index: 914951 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1451079 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1980427 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1070. Min Act: -0.0000

Data Index: 284146 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1748868 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1089942 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0919. Min Act: -0.0000

Data Index: 880825 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1292951 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1053123 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1106458 (The Pile)

Max Activating Token Index: 504

Text #14

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1768393 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1865269 (The Pile)

Max Activating Token Index: 153

Text #16

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0896. Min Act: -0.0000

Data Index: 962112 (The Pile)

Max Activating Token Index: 340

Text #17

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1591324 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1266554 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1679365 (The Pile)

Max Activating Token Index: 738