Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 335 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 1.1417. Min Range: -1.1417

Max Act: 1.1417. Min Act: -0.0003

Data Index: 1257764 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 1.1417. Min Range: -1.1417

Max Act: 1.0785. Min Act: -0.0004

Data Index: 742699 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.1417. Min Range: -1.1417

Max Act: 1.0531. Min Act: -0.0003

Data Index: 176148 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 1.1417. Min Range: -1.1417

Max Act: 1.0003. Min Act: -0.0003

Data Index: 691710 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.9945. Min Act: -0.0003

Data Index: 38853 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.9843. Min Act: -0.0003

Data Index: 1173371 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.9052. Min Act: -0.0003

Data Index: 660347 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8896. Min Act: -0.0003

Data Index: 1064531 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8765. Min Act: -0.0003

Data Index: 799278 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8677. Min Act: -0.0003

Data Index: 42041 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8648. Min Act: -0.0003

Data Index: 1237853 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8837. Min Act: -0.0003

Data Index: 1095737 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8559. Min Act: -0.0003

Data Index: 1000891 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8809. Min Act: -0.0003

Data Index: 1177246 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8454. Min Act: -0.0003

Data Index: 1084226 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8652. Min Act: -0.0003

Data Index: 775899 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8279. Min Act: -0.0003

Data Index: 1234051 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8282. Min Act: -0.0003

Data Index: 382729 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8268. Min Act: -0.0003

Data Index: 769851 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8550. Min Act: -0.0003

Data Index: 555401 (C4 (Web Text))

Max Activating Token Index: 12