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

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

Neuron 453 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: 0.1696. Min Range: -0.1696

Max Act: 0.1696. Min Act: -0.0001

Data Index: 636872 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1572. Min Act: -0.0001

Data Index: 733370 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1098611 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1549. Min Act: -0.0001

Data Index: 212733 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1512. Min Act: -0.0001

Data Index: 644780 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1512. Min Act: -0.0001

Data Index: 108935 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1379. Min Act: -0.0001

Data Index: 73155 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1396. Min Act: -0.0001

Data Index: 473621 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1419. Min Act: -0.0001

Data Index: 601983 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1411. Min Act: -0.0001

Data Index: 850259 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1016988 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1537. Min Act: -0.0001

Data Index: 13094 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1509. Min Act: -0.0001

Data Index: 324875 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1214. Min Act: -0.0001

Data Index: 648282 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1357. Min Act: -0.0001

Data Index: 163847 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1403. Min Act: -0.0001

Data Index: 313570 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1378. Min Act: -0.0001

Data Index: 689536 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1308. Min Act: -0.0001

Data Index: 723726 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1087. Min Act: -0.0001

Data Index: 451088 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1260. Min Act: -0.0001

Data Index: 689809 (C4 (Web Text))

Max Activating Token Index: 209