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

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

Neuron 116 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2242. Min Act: -0.0002

Data Index: 621747 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1568928 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1394. Min Act: -0.0002

Data Index: 937039 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1271815 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1237333 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1195. Min Act: -0.0002

Data Index: 1253306 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.0893. Min Act: -0.0002

Data Index: 560099 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1014. Min Act: -0.0002

Data Index: 142898 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1164. Min Act: -0.0002

Data Index: 702160 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1248752 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1234. Min Act: -0.0002

Data Index: 123796 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1081. Min Act: -0.0002

Data Index: 198845 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1198429 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1113155 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1129. Min Act: -0.0002

Data Index: 789041 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.0914. Min Act: -0.0002

Data Index: 33063 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.0988. Min Act: -0.0002

Data Index: 72108 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.0799. Min Act: -0.0002

Data Index: 206355 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1335327 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.0975. Min Act: -0.0002

Data Index: 806167 (C4 (Web Text))

Max Activating Token Index: 160