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

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

Neuron 758 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: 0.0904. Min Range: -0.0904

Max Act: 0.0904. Min Act: -0.0002

Data Index: 540557 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0812. Min Act: -0.0002

Data Index: 673381 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1266520 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0665. Min Act: -0.0002

Data Index: 224692 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0712. Min Act: -0.0002

Data Index: 145604 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0649. Min Act: -0.0002

Data Index: 962292 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0656. Min Act: -0.0002

Data Index: 52181 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1047761 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0590. Min Act: -0.0002

Data Index: 373855 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0577. Min Act: -0.0002

Data Index: 291736 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0622. Min Act: -0.0002

Data Index: 209792 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0621. Min Act: -0.0002

Data Index: 723108 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0589. Min Act: -0.0002

Data Index: 689191 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0593. Min Act: -0.0002

Data Index: 827825 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0564. Min Act: -0.0002

Data Index: 304672 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1201439 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0540. Min Act: -0.0002

Data Index: 796891 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0540. Min Act: -0.0002

Data Index: 601468 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0570. Min Act: -0.0002

Data Index: 171476 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0557. Min Act: -0.0002

Data Index: 181779 (C4 (Web Text))

Max Activating Token Index: 927