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

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

Neuron 2389 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2692. Min Act: -0.0003

Data Index: 1412278 (Python Code)

Max Activating Token Index: 501

Text #1

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2440. Min Act: -0.0003

Data Index: 1587253 (Python Code)

Max Activating Token Index: 516

Text #2

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2399. Min Act: -0.0003

Data Index: 1431845 (Python Code)

Max Activating Token Index: 594

Text #3

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2280. Min Act: -0.0003

Data Index: 1541728 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2350. Min Act: -0.0002

Data Index: 1509330 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2264. Min Act: -0.0003

Data Index: 1425610 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2207. Min Act: -0.0003

Data Index: 1538165 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2324. Min Act: -0.0003

Data Index: 1492068 (Python Code)

Max Activating Token Index: 283

Text #8

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2169. Min Act: -0.0003

Data Index: 1370429 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2279. Min Act: -0.0002

Data Index: 1636398 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2200. Min Act: -0.0003

Data Index: 1495019 (Python Code)

Max Activating Token Index: 775

Text #11

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2129. Min Act: -0.0003

Data Index: 1392102 (Python Code)

Max Activating Token Index: 630

Text #12

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2166. Min Act: -0.0003

Data Index: 1588534 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2147. Min Act: -0.0003

Data Index: 1615487 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2028. Min Act: -0.0003

Data Index: 1486200 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2029. Min Act: -0.0003

Data Index: 1398654 (Python Code)

Max Activating Token Index: 249

Text #16

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2013. Min Act: -0.0002

Data Index: 1458034 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2094. Min Act: -0.0003

Data Index: 1642782 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2081. Min Act: -0.0002

Data Index: 1519195 (Python Code)

Max Activating Token Index: 496

Text #19

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2105. Min Act: -0.0003

Data Index: 1545847 (Python Code)

Max Activating Token Index: 972