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

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

Neuron 3606 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: 0.1715. Min Range: -0.1715

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1229132 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1225066 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1507. Min Act: -0.0001

Data Index: 898633 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1512. Min Act: -0.0001

Data Index: 451856 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1547. Min Act: -0.0001

Data Index: 916761 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1333788 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1196613 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1298688 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1086406 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1353. Min Act: -0.0001

Data Index: 571677 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1151. Min Act: -0.0001

Data Index: 783151 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1417. Min Act: -0.0001

Data Index: 401554 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1201833 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1242. Min Act: -0.0002

Data Index: 1315665 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1347. Min Act: -0.0001

Data Index: 315905 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1284. Min Act: -0.0001

Data Index: 881333 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1243491 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1227. Min Act: -0.0001

Data Index: 668748 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1333. Min Act: -0.0001

Data Index: 715105 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1301. Min Act: -0.0001

Data Index: 328521 (C4 (Web Text))

Max Activating Token Index: 662