Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2694 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1572003 (Python Code)

Max Activating Token Index: 377

Text #1

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1442368 (Python Code)

Max Activating Token Index: 452

Text #2

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1575090 (Python Code)

Max Activating Token Index: 186

Text #3

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1471140 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1632856 (Python Code)

Max Activating Token Index: 831

Text #5

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1534907 (Python Code)

Max Activating Token Index: 601

Text #6

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1591762 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1634340 (Python Code)

Max Activating Token Index: 681

Text #8

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1378979 (Python Code)

Max Activating Token Index: 380

Text #9

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1553929 (Python Code)

Max Activating Token Index: 439

Text #10

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1488640 (Python Code)

Max Activating Token Index: 521

Text #11

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1404759 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1514544 (Python Code)

Max Activating Token Index: 707

Text #13

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1378457 (Python Code)

Max Activating Token Index: 369

Text #14

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1461914 (Python Code)

Max Activating Token Index: 788

Text #15

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1511593 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1470046 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1610445 (Python Code)

Max Activating Token Index: 147

Text #18

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1574649 (Python Code)

Max Activating Token Index: 377

Text #19

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1405. Min Act: -0.0001

Data Index: 1431485 (Python Code)

Max Activating Token Index: 130