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

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

Neuron 600 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0652. Min Act: -0.0001

Data Index: 682717 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1660. Min Act: -0.0001

Data Index: 879569 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9896. Min Act: -0.0001

Data Index: 89673 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8833. Min Act: -0.0001

Data Index: 562779 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9111. Min Act: -0.0001

Data Index: 1175357 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8964. Min Act: -0.0001

Data Index: 446858 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9816. Min Act: -0.0001

Data Index: 106339 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8395. Min Act: -0.0001

Data Index: 1009193 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9732. Min Act: -0.0001

Data Index: 574712 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8856. Min Act: -0.0001

Data Index: 1005891 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9060. Min Act: -0.0001

Data Index: 1143920 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9207. Min Act: -0.0001

Data Index: 1224400 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8643. Min Act: -0.0001

Data Index: 584966 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8346. Min Act: -0.0001

Data Index: 1169755 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8292. Min Act: -0.0001

Data Index: 1279651 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8788. Min Act: -0.0001

Data Index: 1137209 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8824. Min Act: -0.0001

Data Index: 233735 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8177. Min Act: -0.0001

Data Index: 961264 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8244. Min Act: -0.0001

Data Index: 408545 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8111. Min Act: -0.0001

Data Index: 745137 (C4 (Web Text))

Max Activating Token Index: 462