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

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

Neuron 618 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: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1018188 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0751. Min Act: -0.0002

Data Index: 312528 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1116597 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0675. Min Act: -0.0002

Data Index: 255477 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0663. Min Act: -0.0002

Data Index: 613555 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1068958 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1320485 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1080036 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1175552 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0666. Min Act: -0.0002

Data Index: 686963 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0671. Min Act: -0.0002

Data Index: 483590 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0645. Min Act: -0.0002

Data Index: 201545 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1270438 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0666. Min Act: -0.0002

Data Index: 353837 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0647. Min Act: -0.0002

Data Index: 971890 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0646. Min Act: -0.0002

Data Index: 798282 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0624. Min Act: -0.0002

Data Index: 377613 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1095145 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1277714 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0639. Min Act: -0.0002

Data Index: 330770 (C4 (Web Text))

Max Activating Token Index: 68