Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2972 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1608. Min Act: -0.0003

Data Index: 1557454 (Python Code)

Max Activating Token Index: 152

Text #1

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1513. Min Act: -0.0003

Data Index: 1591475 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1568. Min Act: -0.0003

Data Index: 1587789 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1422. Min Act: -0.0003

Data Index: 1191967 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1394. Min Act: -0.0003

Data Index: 654036 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1351. Min Act: -0.0003

Data Index: 1362889 (Python Code)

Max Activating Token Index: 784

Text #6

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1343. Min Act: -0.0003

Data Index: 1206453 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1321. Min Act: -0.0003

Data Index: 1645568 (Python Code)

Max Activating Token Index: 654

Text #8

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1366. Min Act: -0.0003

Data Index: 1481921 (Python Code)

Max Activating Token Index: 640

Text #9

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1220. Min Act: -0.0003

Data Index: 829145 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1388. Min Act: -0.0003

Data Index: 1360236 (Python Code)

Max Activating Token Index: 244

Text #11

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1368. Min Act: -0.0003

Data Index: 1479391 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1315. Min Act: -0.0003

Data Index: 1450979 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1362. Min Act: -0.0003

Data Index: 1479802 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1343. Min Act: -0.0003

Data Index: 324014 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1289. Min Act: -0.0003

Data Index: 1620098 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1192. Min Act: -0.0003

Data Index: 1550533 (Python Code)

Max Activating Token Index: 1003

Text #17

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1242. Min Act: -0.0003

Data Index: 1361947 (Python Code)

Max Activating Token Index: 131

Text #18

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1283. Min Act: -0.0003

Data Index: 1612330 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1377. Min Act: -0.0003

Data Index: 1412495 (Python Code)

Max Activating Token Index: 191