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

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

Neuron 4348 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1094 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1068823 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1378. Min Act: -0.0000

Data Index: 791112 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1193. Min Act: -0.0000

Data Index: 54805 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1213669 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1249. Min Act: -0.0000

Data Index: 849005 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1143262 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1313862 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1119. Min Act: -0.0000

Data Index: 646875 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1038034 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1143. Min Act: -0.0000

Data Index: 117035 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1127. Min Act: -0.0000

Data Index: 780345 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1091814 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1051. Min Act: -0.0000

Data Index: 968500 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1046. Min Act: 0.0000

Data Index: 117630 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1169165 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1368331 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1034. Min Act: 0.0000

Data Index: 204049 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1068. Min Act: -0.0000

Data Index: 50249 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1041640 (C4 (Web Text))

Max Activating Token Index: 740