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

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

Neuron 81 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: 1.2773. Min Range: -1.2773

Max Act: 1.2773. Min Act: -0.0001

Data Index: 443956 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.2410. Min Act: -0.0001

Data Index: 907392 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1404. Min Act: -0.0001

Data Index: 1021321 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.2053. Min Act: -0.0001

Data Index: 1156387 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1511. Min Act: -0.0001

Data Index: 107044 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1406. Min Act: -0.0001

Data Index: 924444 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1812. Min Act: -0.0001

Data Index: 440806 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1540. Min Act: -0.0001

Data Index: 388967 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0800. Min Act: -0.0001

Data Index: 358407 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0992. Min Act: -0.0001

Data Index: 698195 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1441. Min Act: -0.0001

Data Index: 254412 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1252. Min Act: -0.0001

Data Index: 1352530 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1558. Min Act: -0.0001

Data Index: 509535 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1341922 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0934. Min Act: -0.0001

Data Index: 1262725 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1170. Min Act: -0.0001

Data Index: 220507 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0727. Min Act: -0.0001

Data Index: 1076516 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1275. Min Act: -0.0001

Data Index: 72285 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1005. Min Act: -0.0001

Data Index: 518726 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1008. Min Act: -0.0001

Data Index: 517458 (C4 (Web Text))

Max Activating Token Index: 55