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

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

Neuron 4518 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1589056 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1580591 (Python Code)

Max Activating Token Index: 666

Text #2

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1536761 (Python Code)

Max Activating Token Index: 155

Text #3

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1634228 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1535457 (Python Code)

Max Activating Token Index: 253

Text #5

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1486924 (Python Code)

Max Activating Token Index: 570

Text #6

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6390. Min Act: -0.0000

Data Index: 363553 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1485763 (Python Code)

Max Activating Token Index: 123

Text #8

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1425130 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1494230 (Python Code)

Max Activating Token Index: 383

Text #10

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1572418 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1397982 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1360118 (Python Code)

Max Activating Token Index: 647

Text #13

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1571937 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1438908 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1540471 (Python Code)

Max Activating Token Index: 164

Text #16

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1201390 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1597848 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1576567 (Python Code)

Max Activating Token Index: 561

Text #19

Max Range: 0.7189. Min Range: -0.7189

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1598860 (Python Code)

Max Activating Token Index: 796