Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 345 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0003

Data Index: 366846 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0607. Min Act: -0.0003

Data Index: 435888 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0581. Min Act: -0.0003

Data Index: 546774 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0588. Min Act: -0.0003

Data Index: 383211 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0588. Min Act: -0.0003

Data Index: 16608 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1138419 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0550. Min Act: -0.0003

Data Index: 50612 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1285701 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0568. Min Act: -0.0003

Data Index: 440698 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0554. Min Act: -0.0003

Data Index: 895710 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0544. Min Act: -0.0003

Data Index: 533151 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0539. Min Act: -0.0003

Data Index: 598848 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0571. Min Act: -0.0003

Data Index: 571342 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0516. Min Act: -0.0003

Data Index: 454377 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1015482 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0530. Min Act: -0.0003

Data Index: 396103 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0503. Min Act: -0.0003

Data Index: 390998 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0529. Min Act: -0.0003

Data Index: 218393 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0524. Min Act: -0.0003

Data Index: 68382 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0498. Min Act: -0.0003

Data Index: 810419 (C4 (Web Text))

Max Activating Token Index: 673