Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2312 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.5741. Min Act: -0.0001

Data Index: 1503430 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.3814. Min Act: -0.0001

Data Index: 1572130 (Python Code)

Max Activating Token Index: 503

Text #2

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.3275. Min Act: -0.0001

Data Index: 1374824 (Python Code)

Max Activating Token Index: 304

Text #3

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.3234. Min Act: -0.0001

Data Index: 1395351 (Python Code)

Max Activating Token Index: 220

Text #4

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.3207. Min Act: -0.0001

Data Index: 1429868 (Python Code)

Max Activating Token Index: 574

Text #5

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1583. Min Act: -0.0001

Data Index: 1629289 (Python Code)

Max Activating Token Index: 700

Text #6

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.2978. Min Act: -0.0001

Data Index: 1409722 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.2299. Min Act: -0.0001

Data Index: 1361289 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1985. Min Act: -0.0001

Data Index: 1516659 (Python Code)

Max Activating Token Index: 870

Text #9

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.2640. Min Act: -0.0001

Data Index: 1623351 (Python Code)

Max Activating Token Index: 481

Text #10

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1339. Min Act: -0.0001

Data Index: 1564867 (Python Code)

Max Activating Token Index: 568

Text #11

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.2129. Min Act: -0.0001

Data Index: 1448452 (Python Code)

Max Activating Token Index: 754

Text #12

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1619. Min Act: -0.0001

Data Index: 1438589 (Python Code)

Max Activating Token Index: 822

Text #13

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1897. Min Act: -0.0001

Data Index: 1521236 (Python Code)

Max Activating Token Index: 452

Text #14

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1875. Min Act: -0.0001

Data Index: 1514244 (Python Code)

Max Activating Token Index: 880

Text #15

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1866. Min Act: -0.0001

Data Index: 1598482 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1531. Min Act: -0.0001

Data Index: 1478703 (Python Code)

Max Activating Token Index: 426

Text #17

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1055. Min Act: -0.0001

Data Index: 1370243 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1316. Min Act: -0.0001

Data Index: 1637602 (Python Code)

Max Activating Token Index: 366

Text #19

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.0989. Min Act: -0.0001

Data Index: 1624448 (Python Code)

Max Activating Token Index: 617