Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1499 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0555. Min Act: -0.0002

Data Index: 863830 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0002

Data Index: 939845 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0632. Min Act: -0.0002

Data Index: 961964 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0610. Min Act: -0.0002

Data Index: 234758 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0614. Min Act: -0.0002

Data Index: 705552 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1313310 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0588. Min Act: -0.0002

Data Index: 685097 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0582. Min Act: -0.0002

Data Index: 701559 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1196637 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0556. Min Act: -0.0001

Data Index: 981067 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0525. Min Act: -0.0002

Data Index: 921303 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0595. Min Act: -0.0002

Data Index: 386409 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0511. Min Act: -0.0002

Data Index: 744005 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0570. Min Act: -0.0002

Data Index: 530238 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0625. Min Act: -0.0002

Data Index: 794723 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1142269 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1068827 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0546. Min Act: -0.0002

Data Index: 244097 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0575. Min Act: -0.0002

Data Index: 11814 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0522. Min Act: -0.0002

Data Index: 563329 (C4 (Web Text))

Max Activating Token Index: 614