Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1885 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.4694. Min Act: -0.0002

Data Index: 883338 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.2563. Min Act: -0.0003

Data Index: 715589 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.2577. Min Act: -0.0002

Data Index: 138106 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.2113. Min Act: -0.0003

Data Index: 693256 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.1797. Min Act: -0.0002

Data Index: 310617 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.1734. Min Act: -0.0002

Data Index: 251518 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.1792. Min Act: -0.0002

Data Index: 502525 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.1806. Min Act: -0.0002

Data Index: 210586 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.1551. Min Act: -0.0002

Data Index: 1346200 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.1247. Min Act: -0.0002

Data Index: 461754 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.1221. Min Act: -0.0002

Data Index: 303873 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.1243. Min Act: -0.0002

Data Index: 138930 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.0929. Min Act: -0.0002

Data Index: 697191 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.1043. Min Act: -0.0002

Data Index: 442617 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.0638. Min Act: -0.0002

Data Index: 1338225 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.0664. Min Act: -0.0002

Data Index: 345760 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.0772. Min Act: -0.0002

Data Index: 1309702 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.0735. Min Act: -0.0002

Data Index: 55600 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.0570. Min Act: -0.0002

Data Index: 1192913 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.4694. Min Range: -1.4694

Max Act: 1.0603. Min Act: -0.0002

Data Index: 1074021 (C4 (Web Text))

Max Activating Token Index: 118