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

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

Neuron 4178 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: 1.3595. Min Range: -1.3595

Max Act: 1.3385. Min Act: -0.0002

Data Index: 1401571 (Python Code)

Max Activating Token Index: 730

Text #1

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.3428. Min Act: -0.0002

Data Index: 1461983 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.2035. Min Act: -0.0002

Data Index: 1540309 (Python Code)

Max Activating Token Index: 169

Text #3

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.2923. Min Act: -0.0002

Data Index: 1395668 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.3595. Min Act: -0.0002

Data Index: 1637705 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.3005. Min Act: -0.0002

Data Index: 1438895 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1832. Min Act: -0.0002

Data Index: 1625238 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1612. Min Act: -0.0002

Data Index: 1541056 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1573. Min Act: -0.0002

Data Index: 1574501 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1072. Min Act: -0.0002

Data Index: 1418340 (Python Code)

Max Activating Token Index: 686

Text #10

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1703. Min Act: -0.0002

Data Index: 1406833 (Python Code)

Max Activating Token Index: 402

Text #11

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.2228. Min Act: -0.0002

Data Index: 1535266 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.2339. Min Act: -0.0002

Data Index: 1614477 (Python Code)

Max Activating Token Index: 161

Text #13

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1375. Min Act: -0.0002

Data Index: 1525125 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1285. Min Act: -0.0002

Data Index: 1461062 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1812. Min Act: -0.0002

Data Index: 1429043 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1134. Min Act: -0.0002

Data Index: 1382246 (Python Code)

Max Activating Token Index: 303

Text #17

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0940. Min Act: -0.0002

Data Index: 1461275 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0735. Min Act: -0.0002

Data Index: 1550075 (Python Code)

Max Activating Token Index: 320

Text #19

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1337. Min Act: -0.0002

Data Index: 1370688 (Python Code)

Max Activating Token Index: 7