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

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

Neuron 2992 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1650. Min Act: -0.0002

Data Index: 1535024 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1524. Min Act: -0.0002

Data Index: 1433828 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1409. Min Act: -0.0002

Data Index: 158330 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1391. Min Act: -0.0002

Data Index: 1635622 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1386. Min Act: -0.0002

Data Index: 1442780 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1419700 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1275. Min Act: -0.0002

Data Index: 1580140 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1401247 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1446707 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1235. Min Act: -0.0002

Data Index: 1627603 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1230. Min Act: -0.0002

Data Index: 1645060 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1206. Min Act: -0.0002

Data Index: 650182 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1488257 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1590718 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1130. Min Act: -0.0002

Data Index: 1472317 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1131. Min Act: -0.0002

Data Index: 593985 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1374938 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1153. Min Act: -0.0002

Data Index: 151289 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1522471 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1408638 (Python Code)

Max Activating Token Index: 29