Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2496 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1770. Min Act: -0.0002

Data Index: 1481994 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1499. Min Act: -0.0002

Data Index: 1542771 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1452. Min Act: -0.0002

Data Index: 1411427 (Python Code)

Max Activating Token Index: 416

Text #3

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1365. Min Act: -0.0002

Data Index: 1626332 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1512. Min Act: -0.0002

Data Index: 265727 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1421. Min Act: -0.0002

Data Index: 1621230 (Python Code)

Max Activating Token Index: 318

Text #6

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1581431 (Python Code)

Max Activating Token Index: 505

Text #7

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1377. Min Act: -0.0002

Data Index: 1432551 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1346. Min Act: -0.0002

Data Index: 1628983 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1668. Min Act: -0.0002

Data Index: 1650710 (Python Code)

Max Activating Token Index: 240

Text #10

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1487867 (Python Code)

Max Activating Token Index: 101

Text #11

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1191. Min Act: -0.0002

Data Index: 1458702 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1184. Min Act: -0.0002

Data Index: 1543997 (Python Code)

Max Activating Token Index: 338

Text #13

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1443932 (Python Code)

Max Activating Token Index: 942

Text #14

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1254. Min Act: -0.0002

Data Index: 1480797 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1238. Min Act: -0.0002

Data Index: 1451600 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1374770 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1273. Min Act: -0.0002

Data Index: 279237 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1593. Min Act: -0.0002

Data Index: 1620946 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1244. Min Act: -0.0002

Data Index: 1561968 (Python Code)

Max Activating Token Index: 90