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

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

Neuron 4626 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0550. Min Range: -1.0550

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1548909 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1394118 (Python Code)

Max Activating Token Index: 684

Text #2

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.9468. Min Act: -0.0001

Data Index: 1361900 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.9866. Min Act: -0.0000

Data Index: 171339 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1432033 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1153101 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.9455. Min Act: -0.0000

Data Index: 946236 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1748 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8709. Min Act: -0.0000

Data Index: 217626 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8779. Min Act: -0.0001

Data Index: 1392404 (Python Code)

Max Activating Token Index: 294

Text #10

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8406. Min Act: -0.0001

Data Index: 1594871 (Python Code)

Max Activating Token Index: 407

Text #11

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1518883 (Python Code)

Max Activating Token Index: 809

Text #12

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1614335 (Python Code)

Max Activating Token Index: 726

Text #13

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1221929 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1154560 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7621. Min Act: -0.0001

Data Index: 1371122 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.8050. Min Act: -0.0000

Data Index: 586770 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7666. Min Act: -0.0000

Data Index: 618650 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7578. Min Act: -0.0000

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.0550. Min Range: -1.0550

Max Act: 0.7885. Min Act: -0.0000

Data Index: 272471 (C4 (Web Text))

Max Activating Token Index: 47