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

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

Neuron 3631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0002

Data Index: 909880 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0778. Min Act: -0.0002

Data Index: 546324 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0738. Min Act: -0.0002

Data Index: 381702 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1076252 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0704. Min Act: -0.0002

Data Index: 437822 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0683. Min Act: -0.0002

Data Index: 436865 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0679. Min Act: -0.0002

Data Index: 303969 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1343431 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1195494 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0647. Min Act: -0.0002

Data Index: 908887 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1201597 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1261750 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0631. Min Act: -0.0002

Data Index: 202818 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0620. Min Act: -0.0002

Data Index: 649723 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0611. Min Act: -0.0002

Data Index: 487988 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1133891 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0595. Min Act: -0.0002

Data Index: 760483 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0593. Min Act: -0.0002

Data Index: 712178 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0618. Min Act: -0.0002

Data Index: 283544 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0587. Min Act: -0.0002

Data Index: 394419 (C4 (Web Text))

Max Activating Token Index: 359