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

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

Neuron 40 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8648. Min Act: -0.0000

Data Index: 760902 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8239. Min Act: -0.0000

Data Index: 77728 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7713. Min Act: -0.0000

Data Index: 949665 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1141513 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1355900 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1236714 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6728. Min Act: -0.0000

Data Index: 885268 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6301. Min Act: -0.0000

Data Index: 670067 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1271888 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6602. Min Act: -0.0000

Data Index: 218562 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1227620 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6585. Min Act: -0.0000

Data Index: 211517 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6241. Min Act: -0.0000

Data Index: 791782 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6432. Min Act: -0.0000

Data Index: 780264 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6307. Min Act: -0.0000

Data Index: 899567 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1347166 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6389. Min Act: -0.0000

Data Index: 822946 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5915. Min Act: -0.0000

Data Index: 899007 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1232086 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6172. Min Act: -0.0000

Data Index: 238470 (C4 (Web Text))

Max Activating Token Index: 369