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

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

Neuron 5005 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: 0.9690. Min Range: -0.9690

Max Act: 0.9690. Min Act: -0.0000

Data Index: 698150 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.9322. Min Act: -0.0000

Data Index: 329487 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1104702 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7812. Min Act: -0.0000

Data Index: 295650 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1315255 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.4394. Min Act: -0.0000

Data Index: 449598 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1289464 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7327. Min Act: -0.0000

Data Index: 489778 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6442. Min Act: -0.0000

Data Index: 696200 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6378. Min Act: -0.0000

Data Index: 142413 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6324. Min Act: -0.0000

Data Index: 937477 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6089. Min Act: -0.0001

Data Index: 137653 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6340. Min Act: -0.0000

Data Index: 574940 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1020030 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.4571. Min Act: -0.0000

Data Index: 649401 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1093647 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5773. Min Act: -0.0000

Data Index: 452790 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1337441 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6037. Min Act: -0.0000

Data Index: 896135 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5623. Min Act: -0.0000

Data Index: 832722 (C4 (Web Text))

Max Activating Token Index: 1011