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

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

Neuron 2458 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1423022 (Python Code)

Max Activating Token Index: 816

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1484427 (Python Code)

Max Activating Token Index: 184

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1621600 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1509966 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1617696 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1536409 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1570953 (Python Code)

Max Activating Token Index: 612

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1465569 (Python Code)

Max Activating Token Index: 876

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1565633 (Python Code)

Max Activating Token Index: 242

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1411228 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1546718 (Python Code)

Max Activating Token Index: 286

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1414596 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1420579 (Python Code)

Max Activating Token Index: 896

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1556973 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1445606 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1373916 (Python Code)

Max Activating Token Index: 165

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1451739 (Python Code)

Max Activating Token Index: 427

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1486948 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1631032 (Python Code)

Max Activating Token Index: 707

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1374814 (Python Code)

Max Activating Token Index: 359