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

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

Neuron 1957 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: 0.1570. Min Range: -0.1570

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1589169 (Python Code)

Max Activating Token Index: 1000

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1616027 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1590787 (Python Code)

Max Activating Token Index: 821

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1382214 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1607320 (Python Code)

Max Activating Token Index: 180

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1366480 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1611172 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1398853 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1475788 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1465087 (Python Code)

Max Activating Token Index: 633

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1421428 (Python Code)

Max Activating Token Index: 549

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1515835 (Python Code)

Max Activating Token Index: 718

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1359930 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1437083 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1382320 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1550495 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1401690 (Python Code)

Max Activating Token Index: 1018

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1398403 (Python Code)

Max Activating Token Index: 968

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1536936 (Python Code)

Max Activating Token Index: 456

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1613708 (Python Code)

Max Activating Token Index: 549