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

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

Neuron 2652 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: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0001

Data Index: 210986 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0617. Min Act: -0.0001

Data Index: 956476 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0494. Min Act: -0.0001

Data Index: 274961 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0607. Min Act: -0.0002

Data Index: 970976 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0550. Min Act: -0.0001

Data Index: 976210 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0511. Min Act: -0.0001

Data Index: 949324 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0475. Min Act: -0.0002

Data Index: 692110 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0492. Min Act: -0.0001

Data Index: 593357 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1304223 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0434. Min Act: -0.0001

Data Index: 737102 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1617274 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1261501 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0490. Min Act: -0.0001

Data Index: 850181 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0476. Min Act: -0.0001

Data Index: 745083 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1307988 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1275982 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0440. Min Act: -0.0001

Data Index: 950140 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0440. Min Act: -0.0001

Data Index: 377432 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0419. Min Act: -0.0001

Data Index: 799711 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1105610 (C4 (Web Text))

Max Activating Token Index: 481