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

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

Neuron 1547 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1162039 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5708. Min Act: -0.0000

Data Index: 891480 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1087640 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5578. Min Act: -0.0001

Data Index: 128141 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1176584 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5433. Min Act: -0.0001

Data Index: 590804 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5545. Min Act: -0.0000

Data Index: 796306 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5500. Min Act: -0.0000

Data Index: 296725 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5299. Min Act: -0.0000

Data Index: 307465 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1158294 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5128. Min Act: -0.0000

Data Index: 799447 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1060764 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1038455 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5442. Min Act: -0.0000

Data Index: 281907 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5087. Min Act: -0.0000

Data Index: 780512 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5119. Min Act: -0.0000

Data Index: 582467 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5059. Min Act: -0.0000

Data Index: 658423 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5029. Min Act: -0.0000

Data Index: 167863 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1080079 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5156. Min Act: -0.0000

Data Index: 139913 (C4 (Web Text))

Max Activating Token Index: 112