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

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

Neuron 243 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1513198 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1568254 (Python Code)

Max Activating Token Index: 651

Text #2

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1362492 (Python Code)

Max Activating Token Index: 127

Text #3

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1617106 (Python Code)

Max Activating Token Index: 196

Text #4

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1462. Min Act: -0.0001

Data Index: 1383018 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1524602 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1419084 (Python Code)

Max Activating Token Index: 650

Text #7

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1528349 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1333. Min Act: -0.0001

Data Index: 1605876 (Python Code)

Max Activating Token Index: 510

Text #9

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1636908 (Python Code)

Max Activating Token Index: 516

Text #10

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1431297 (Python Code)

Max Activating Token Index: 862

Text #11

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1448474 (Python Code)

Max Activating Token Index: 232

Text #12

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1570955 (Python Code)

Max Activating Token Index: 810

Text #13

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1472263 (Python Code)

Max Activating Token Index: 280

Text #14

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1608741 (Python Code)

Max Activating Token Index: 273

Text #15

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1573040 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1413543 (Python Code)

Max Activating Token Index: 589

Text #17

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1556318 (Python Code)

Max Activating Token Index: 96

Text #18

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1489580 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1419865 (Python Code)

Max Activating Token Index: 164