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

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

Neuron 1929 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1578307 (Python Code)

Max Activating Token Index: 790

Text #1

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1461849 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1541. Min Act: -0.0001

Data Index: 1401270 (Python Code)

Max Activating Token Index: 193

Text #3

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1684. Min Act: -0.0001

Data Index: 1613638 (Python Code)

Max Activating Token Index: 874

Text #4

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1574554 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1411193 (Python Code)

Max Activating Token Index: 110

Text #6

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1382402 (Python Code)

Max Activating Token Index: 760

Text #7

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1513230 (Python Code)

Max Activating Token Index: 21

Text #8

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1591726 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1611254 (Python Code)

Max Activating Token Index: 255

Text #10

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1556302 (Python Code)

Max Activating Token Index: 854

Text #11

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1529107 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1436. Min Act: -0.0001

Data Index: 1414936 (Python Code)

Max Activating Token Index: 54

Text #13

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1530472 (Python Code)

Max Activating Token Index: 309

Text #14

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1603250 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1477302 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1656895 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1427708 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1351. Min Act: -0.0001

Data Index: 1483954 (Python Code)

Max Activating Token Index: 419

Text #19

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1549255 (Python Code)

Max Activating Token Index: 188