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

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

Neuron 1887 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1362094 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1457750 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1333. Min Act: -0.0001

Data Index: 1482361 (Python Code)

Max Activating Token Index: 467

Text #3

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1466597 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1580067 (Python Code)

Max Activating Token Index: 213

Text #5

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1365430 (Python Code)

Max Activating Token Index: 393

Text #6

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1530076 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1427727 (Python Code)

Max Activating Token Index: 648

Text #8

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1593919 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1570255 (Python Code)

Max Activating Token Index: 249

Text #10

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1584059 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1514898 (Python Code)

Max Activating Token Index: 106

Text #12

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1550151 (Python Code)

Max Activating Token Index: 434

Text #13

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1409787 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1545069 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1646780 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1403033 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1529195 (Python Code)

Max Activating Token Index: 111

Text #18

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1510131 (Python Code)

Max Activating Token Index: 121

Text #19

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1617668 (Python Code)

Max Activating Token Index: 86