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

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

Neuron 3657 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: 0.0919. Min Range: -0.0919

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1139641 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0792. Min Act: -0.0002

Data Index: 90038 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0704. Min Act: -0.0002

Data Index: 553765 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0749. Min Act: -0.0002

Data Index: 593603 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0666. Min Act: -0.0002

Data Index: 951816 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0627. Min Act: -0.0002

Data Index: 885553 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0672. Min Act: -0.0002

Data Index: 898885 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1350655 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0594. Min Act: -0.0002

Data Index: 263887 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0638. Min Act: -0.0002

Data Index: 47293 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1096573 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0605. Min Act: -0.0002

Data Index: 887539 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0580. Min Act: -0.0002

Data Index: 748104 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0585. Min Act: -0.0002

Data Index: 429119 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0580. Min Act: -0.0002

Data Index: 999565 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0559. Min Act: -0.0002

Data Index: 924630 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0512. Min Act: -0.0002

Data Index: 948968 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0556. Min Act: -0.0002

Data Index: 544871 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1262372 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0600. Min Act: -0.0002

Data Index: 449457 (C4 (Web Text))

Max Activating Token Index: 88