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

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

Neuron 3693 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: 0.1619. Min Range: -0.1619

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1629366 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1433612 (Python Code)

Max Activating Token Index: 256

Text #2

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1366991 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1611110 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1395294 (Python Code)

Max Activating Token Index: 997

Text #5

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1614902 (Python Code)

Max Activating Token Index: 324

Text #6

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1414592 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1613904 (Python Code)

Max Activating Token Index: 911

Text #8

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1505055 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1552357 (Python Code)

Max Activating Token Index: 656

Text #10

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1520325 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1577216 (Python Code)

Max Activating Token Index: 516

Text #12

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1448139 (Python Code)

Max Activating Token Index: 970

Text #13

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1524801 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1599775 (Python Code)

Max Activating Token Index: 678

Text #15

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1441829 (Python Code)

Max Activating Token Index: 244

Text #16

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1575902 (Python Code)

Max Activating Token Index: 838

Text #17

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1446814 (Python Code)

Max Activating Token Index: 383

Text #18

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1513058 (Python Code)

Max Activating Token Index: 651

Text #19

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1527105 (Python Code)

Max Activating Token Index: 953