Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1176 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1244. Min Act: -0.0002

Data Index: 1386758 (Python Code)

Max Activating Token Index: 368

Text #1

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1141. Min Act: 0.0002

Data Index: 1484879 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1079. Min Act: 0.0001

Data Index: 1460276 (Python Code)

Max Activating Token Index: 551

Text #3

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1547332 (Python Code)

Max Activating Token Index: 389

Text #4

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1077. Min Act: 0.0002

Data Index: 1363044 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1639133 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1563424 (Python Code)

Max Activating Token Index: 788

Text #7

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1582088 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1403805 (Python Code)

Max Activating Token Index: 186

Text #9

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1359867 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0914. Min Act: 0.0001

Data Index: 1526933 (Python Code)

Max Activating Token Index: 498

Text #11

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1543708 (Python Code)

Max Activating Token Index: 210

Text #12

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0901. Min Act: 0.0001

Data Index: 1584976 (Python Code)

Max Activating Token Index: 614

Text #13

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0909. Min Act: 0.0006

Data Index: 1552171 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0921. Min Act: 0.0000

Data Index: 1648346 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1565091 (Python Code)

Max Activating Token Index: 731

Text #16

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1442768 (Python Code)

Max Activating Token Index: 278

Text #17

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0865. Min Act: 0.0003

Data Index: 1392836 (Python Code)

Max Activating Token Index: 604

Text #18

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1495079 (Python Code)

Max Activating Token Index: 644

Text #19

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0906. Min Act: 0.0004

Data Index: 1500722 (Python Code)

Max Activating Token Index: 813