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

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

Neuron 392 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.8881. Min Act: -0.0000

Data Index: 142492 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.7391. Min Act: -0.0000

Data Index: 381172 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1047010 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.7259. Min Act: -0.0000

Data Index: 658224 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6975. Min Act: -0.0000

Data Index: 475576 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1200223 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.7045. Min Act: -0.0000

Data Index: 116067 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1129289 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.7147. Min Act: -0.0000

Data Index: 482410 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6871. Min Act: -0.0000

Data Index: 293718 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6437. Min Act: -0.0000

Data Index: 592883 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1066961 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6766. Min Act: -0.0000

Data Index: 940970 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6534. Min Act: -0.0000

Data Index: 960233 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1247949 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6573. Min Act: -0.0000

Data Index: 77412 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6713. Min Act: -0.0000

Data Index: 96380 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1136126 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6407. Min Act: -0.0000

Data Index: 426623 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6115. Min Act: -0.0000

Data Index: 197002 (C4 (Web Text))

Max Activating Token Index: 330