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

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

Neuron 4386 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.4536. Min Act: -0.0000

Data Index: 943931 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.1775. Min Act: -0.0000

Data Index: 513342 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.5642. Min Act: -0.0000

Data Index: 10838 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.4201. Min Act: -0.0000

Data Index: 725473 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.1741. Min Act: -0.0000

Data Index: 357332 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.2629. Min Act: -0.0000

Data Index: 175678 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.0919. Min Act: -0.0000

Data Index: 1070595 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.0975. Min Act: -0.0000

Data Index: 736376 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.0924. Min Act: -0.0000

Data Index: 313249 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 2.5642. Min Range: -2.5642

Max Act: 2.0747. Min Act: -0.0000

Data Index: 171963 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.7027. Min Act: -0.0000

Data Index: 496427 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.7219. Min Act: -0.0000

Data Index: 827193 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.7125. Min Act: -0.0000

Data Index: 152123 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.9897. Min Act: -0.0000

Data Index: 697537 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1206881 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.8621. Min Act: -0.0000

Data Index: 953708 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.7544. Min Act: -0.0000

Data Index: 658689 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.9677. Min Act: -0.0000

Data Index: 346495 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.9646. Min Act: -0.0000

Data Index: 217053 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 2.5642. Min Range: -2.5642

Max Act: 1.6719. Min Act: -0.0000

Data Index: 1253748 (C4 (Web Text))

Max Activating Token Index: 760