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

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

Neuron 3685 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1172909 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0777. Min Act: -0.0002

Data Index: 553813 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0729. Min Act: -0.0002

Data Index: 23976 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0682. Min Act: -0.0002

Data Index: 28642 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1162735 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0615. Min Act: -0.0002

Data Index: 230433 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0616. Min Act: -0.0002

Data Index: 861718 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0597. Min Act: -0.0002

Data Index: 833717 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1225373 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0595. Min Act: -0.0002

Data Index: 115834 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1103525 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1125748 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0575. Min Act: -0.0002

Data Index: 859275 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0553. Min Act: -0.0003

Data Index: 111433 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0550. Min Act: -0.0002

Data Index: 847939 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1049290 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0546. Min Act: -0.0002

Data Index: 899518 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1348902 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0516. Min Act: -0.0003

Data Index: 509825 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0526. Min Act: -0.0002

Data Index: 387176 (C4 (Web Text))

Max Activating Token Index: 368