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

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

Neuron 1723 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1192. Min Act: -0.0004

Data Index: 1376481 (Python Code)

Max Activating Token Index: 1003

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1197. Min Act: -0.0004

Data Index: 1432890 (Python Code)

Max Activating Token Index: 307

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1236. Min Act: -0.0004

Data Index: 1376448 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1171. Min Act: -0.0004

Data Index: 1600908 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0004

Data Index: 1483634 (Python Code)

Max Activating Token Index: 330

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1170. Min Act: -0.0004

Data Index: 1407494 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1192. Min Act: -0.0004

Data Index: 1375795 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1144. Min Act: -0.0004

Data Index: 1401424 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1233. Min Act: -0.0004

Data Index: 1399431 (Python Code)

Max Activating Token Index: 1002

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1050. Min Act: -0.0004

Data Index: 1609848 (Python Code)

Max Activating Token Index: 779

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1179. Min Act: -0.0004

Data Index: 1534999 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1179. Min Act: -0.0004

Data Index: 1426439 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1135. Min Act: -0.0004

Data Index: 1551272 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1074. Min Act: -0.0004

Data Index: 1387003 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1116. Min Act: -0.0004

Data Index: 1578337 (Python Code)

Max Activating Token Index: 998

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1166. Min Act: -0.0004

Data Index: 1538514 (Python Code)

Max Activating Token Index: 1008

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1160. Min Act: -0.0004

Data Index: 1601974 (Python Code)

Max Activating Token Index: 309

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1118. Min Act: -0.0004

Data Index: 1618353 (Python Code)

Max Activating Token Index: 356

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1121. Min Act: -0.0004

Data Index: 1585399 (Python Code)

Max Activating Token Index: 999

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1206. Min Act: -0.0004

Data Index: 1557962 (Python Code)

Max Activating Token Index: 1003