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

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

Neuron 4648 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.7778. Min Act: -0.0000

Data Index: 1591347 (Python Code)

Max Activating Token Index: 953

Text #1

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.7868. Min Act: -0.0000

Data Index: 1464177 (Python Code)

Max Activating Token Index: 627

Text #2

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.7283. Min Act: -0.0000

Data Index: 1484890 (Python Code)

Max Activating Token Index: 559

Text #3

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.8226. Min Act: -0.0000

Data Index: 1656726 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5869. Min Act: -0.0000

Data Index: 1545922 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5759. Min Act: -0.0000

Data Index: 1530876 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1444676 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5433. Min Act: -0.0000

Data Index: 1631576 (Python Code)

Max Activating Token Index: 998

Text #8

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.6135. Min Act: -0.0000

Data Index: 1448919 (Python Code)

Max Activating Token Index: 576

Text #9

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5254. Min Act: -0.0000

Data Index: 1649349 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5193. Min Act: -0.0000

Data Index: 1551954 (Python Code)

Max Activating Token Index: 535

Text #11

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1568258 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5102. Min Act: -0.0000

Data Index: 1362547 (Python Code)

Max Activating Token Index: 447

Text #13

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1409818 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5167. Min Act: -0.0000

Data Index: 1505777 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5149. Min Act: -0.0000

Data Index: 1563848 (Python Code)

Max Activating Token Index: 484

Text #16

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5056. Min Act: -0.0000

Data Index: 1468694 (Python Code)

Max Activating Token Index: 362

Text #17

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5118. Min Act: -0.0000

Data Index: 1577849 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5107. Min Act: -0.0000

Data Index: 1578147 (Python Code)

Max Activating Token Index: 487

Text #19

Max Range: 1.8226. Min Range: -1.8226

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1648194 (Python Code)

Max Activating Token Index: 456