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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4989 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.7195. Min Act: -0.0000

Data Index: 699641 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1025195 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6622. Min Act: -0.0000

Data Index: 351322 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6433. Min Act: -0.0000

Data Index: 13108 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6557. Min Act: -0.0000

Data Index: 365428 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6114. Min Act: -0.0000

Data Index: 394994 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1004121 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6071. Min Act: -0.0000

Data Index: 555389 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5303. Min Act: -0.0000

Data Index: 232122 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5641. Min Act: -0.0000

Data Index: 729290 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5905. Min Act: -0.0000

Data Index: 920491 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1285110 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5753. Min Act: -0.0000

Data Index: 163461 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5382. Min Act: -0.0000

Data Index: 416304 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5836. Min Act: -0.0000

Data Index: 454191 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5483. Min Act: -0.0000

Data Index: 681723 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1069350 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1048397 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1215396 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1120260 (C4 (Web Text))

Max Activating Token Index: 39