Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2515 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1970. Min Act: -0.0000

Data Index: 241296 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1379. Min Act: -0.0000

Data Index: 922223 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1550. Min Act: -0.0000

Data Index: 308677 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1382. Min Act: -0.0000

Data Index: 844238 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1235. Min Act: -0.0000

Data Index: 214960 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1281. Min Act: -0.0000

Data Index: 994522 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1201838 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1145. Min Act: -0.0000

Data Index: 93778 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1263787 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1186. Min Act: -0.0000

Data Index: 228444 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1208. Min Act: -0.0000

Data Index: 664844 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1118. Min Act: -0.0000

Data Index: 58545 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1154. Min Act: -0.0000

Data Index: 160400 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1119. Min Act: -0.0000

Data Index: 564847 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1042478 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1066. Min Act: -0.0000

Data Index: 327713 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1014. Min Act: -0.0000

Data Index: 95684 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1065687 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.0978. Min Act: -0.0000

Data Index: 378264 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.0949. Min Act: -0.0000

Data Index: 88367 (C4 (Web Text))

Max Activating Token Index: 14