Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.4878. Min Act: -0.0001

Data Index: 93936 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.2375. Min Act: -0.0001

Data Index: 778217 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1562. Min Act: -0.0001

Data Index: 745654 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.2165. Min Act: -0.0001

Data Index: 688222 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1706. Min Act: -0.0001

Data Index: 378476 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1111. Min Act: -0.0001

Data Index: 1106105 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0238. Min Act: -0.0001

Data Index: 1002577 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1209. Min Act: -0.0001

Data Index: 219995 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0568. Min Act: -0.0001

Data Index: 523413 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0883. Min Act: -0.0001

Data Index: 1261011 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.1046. Min Act: -0.0001

Data Index: 466646 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0773. Min Act: -0.0001

Data Index: 443009 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0234. Min Act: -0.0001

Data Index: 776183 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0698. Min Act: -0.0001

Data Index: 168356 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0657. Min Act: -0.0001

Data Index: 252296 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0219. Min Act: -0.0001

Data Index: 181551 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0228. Min Act: -0.0001

Data Index: 430500 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 1.4878. Min Range: -1.4878

Max Act: 1.0592. Min Act: -0.0001

Data Index: 773779 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 1.4878. Min Range: -1.4878

Max Act: 0.9475. Min Act: -0.0001

Data Index: 621299 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.4878. Min Range: -1.4878

Max Act: 0.9732. Min Act: -0.0001

Data Index: 771548 (C4 (Web Text))

Max Activating Token Index: 177