Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1091 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1624282 (Python Code)

Max Activating Token Index: 599

Text #1

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1583399 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1517140 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1501618 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1589176 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1519773 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1399213 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1502806 (Python Code)

Max Activating Token Index: 913

Text #8

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1631522 (Python Code)

Max Activating Token Index: 742

Text #9

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1643705 (Python Code)

Max Activating Token Index: 800

Text #10

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1493284 (Python Code)

Max Activating Token Index: 208

Text #11

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1396961 (Python Code)

Max Activating Token Index: 523

Text #12

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1601167 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1395944 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1414686 (Python Code)

Max Activating Token Index: 207

Text #15

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1454090 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1493697 (Python Code)

Max Activating Token Index: 421

Text #17

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1644454 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1602111 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1432923 (Python Code)

Max Activating Token Index: 501