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

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

Neuron 5931 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3533. Min Act: -0.0001

Data Index: 534582 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.4317. Min Act: -0.0001

Data Index: 1021866 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.1452. Min Act: -0.0001

Data Index: 319449 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.2016. Min Act: -0.0001

Data Index: 295425 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.4317. Min Range: -1.4317

Max Act: 0.9980. Min Act: -0.0001

Data Index: 1227660 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.2000. Min Act: -0.0001

Data Index: 795264 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.0885. Min Act: -0.0001

Data Index: 70857 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.0717. Min Act: -0.0001

Data Index: 913402 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.1035. Min Act: -0.0001

Data Index: 677990 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.0423. Min Act: -0.0001

Data Index: 225739 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.0171. Min Act: -0.0001

Data Index: 6211 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.4317. Min Range: -1.4317

Max Act: 0.9590. Min Act: -0.0001

Data Index: 1202533 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.1202. Min Act: -0.0001

Data Index: 185640 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.0319. Min Act: -0.0001

Data Index: 451628 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 1.4317. Min Range: -1.4317

Max Act: 0.9363. Min Act: -0.0001

Data Index: 339889 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 1.4317. Min Range: -1.4317

Max Act: 0.9035. Min Act: -0.0001

Data Index: 540839 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 1.4317. Min Range: -1.4317

Max Act: 0.8566. Min Act: -0.0001

Data Index: 809728 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 1.4317. Min Range: -1.4317

Max Act: 0.8429. Min Act: -0.0001

Data Index: 101185 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 1.4317. Min Range: -1.4317

Max Act: 0.9414. Min Act: -0.0001

Data Index: 362939 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 1.4317. Min Range: -1.4317

Max Act: 0.9993. Min Act: -0.0001

Data Index: 496954 (C4 (Web Text))

Max Activating Token Index: 850