Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 180 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1453. Min Act: -0.0006

Data Index: 1588974 (Python Code)

Max Activating Token Index: 453

Text #1

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1431. Min Act: -0.0006

Data Index: 1470535 (Python Code)

Max Activating Token Index: 522

Text #2

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1412. Min Act: -0.0006

Data Index: 1444063 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1461. Min Act: -0.0006

Data Index: 1456027 (Python Code)

Max Activating Token Index: 895

Text #4

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1464. Min Act: -0.0006

Data Index: 1378288 (Python Code)

Max Activating Token Index: 668

Text #5

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1386. Min Act: -0.0006

Data Index: 1500303 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1497. Min Act: -0.0006

Data Index: 1446496 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1333. Min Act: -0.0006

Data Index: 1607691 (Python Code)

Max Activating Token Index: 710

Text #8

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1430. Min Act: -0.0006

Data Index: 1574586 (Python Code)

Max Activating Token Index: 621

Text #9

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1595. Min Act: -0.0006

Data Index: 1382252 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1363. Min Act: -0.0006

Data Index: 1445298 (Python Code)

Max Activating Token Index: 691

Text #11

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1360. Min Act: -0.0006

Data Index: 1568837 (Python Code)

Max Activating Token Index: 513

Text #12

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1407. Min Act: -0.0006

Data Index: 1574332 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1386. Min Act: -0.0006

Data Index: 1387277 (Python Code)

Max Activating Token Index: 381

Text #14

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1380. Min Act: -0.0006

Data Index: 1534432 (Python Code)

Max Activating Token Index: 761

Text #15

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1429. Min Act: -0.0006

Data Index: 1372706 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1374. Min Act: -0.0006

Data Index: 1649738 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1372. Min Act: -0.0006

Data Index: 1613752 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1315. Min Act: -0.0006

Data Index: 1368316 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1367. Min Act: -0.0006

Data Index: 1374711 (Python Code)

Max Activating Token Index: 652