Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 119 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0004

Data Index: 386799 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0624. Min Act: -0.0003

Data Index: 62470 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0589. Min Act: -0.0003

Data Index: 122217 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0574. Min Act: -0.0003

Data Index: 413892 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0569. Min Act: -0.0003

Data Index: 786616 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0575. Min Act: -0.0004

Data Index: 1139035 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0603. Min Act: -0.0003

Data Index: 785985 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0567. Min Act: -0.0003

Data Index: 85712 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0571. Min Act: -0.0003

Data Index: 931806 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1347723 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0587. Min Act: -0.0004

Data Index: 644448 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0576. Min Act: -0.0004

Data Index: 561776 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0553. Min Act: -0.0004

Data Index: 1030875 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0542. Min Act: -0.0003

Data Index: 854863 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0558. Min Act: -0.0003

Data Index: 292695 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0558. Min Act: -0.0003

Data Index: 722944 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0551. Min Act: -0.0004

Data Index: 933756 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0554. Min Act: -0.0004

Data Index: 1137772 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0555. Min Act: -0.0003

Data Index: 525579 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0577. Min Act: -0.0003

Data Index: 311247 (C4 (Web Text))

Max Activating Token Index: 22