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

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

Neuron 884 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: 0.0872. Min Range: -0.0872

Max Act: 0.0872. Min Act: -0.0003

Data Index: 1181537 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0797. Min Act: -0.0003

Data Index: 1224777 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0785. Min Act: -0.0003

Data Index: 3618 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0751. Min Act: -0.0003

Data Index: 956984 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0739. Min Act: -0.0003

Data Index: 394929 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0720. Min Act: -0.0003

Data Index: 1214132 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0732. Min Act: -0.0003

Data Index: 839937 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0691. Min Act: -0.0003

Data Index: 1171751 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0760. Min Act: -0.0003

Data Index: 951639 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0698. Min Act: -0.0003

Data Index: 560429 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0731. Min Act: -0.0003

Data Index: 11708 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0709. Min Act: -0.0003

Data Index: 839003 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1347255 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0613. Min Act: -0.0003

Data Index: 133298 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0694. Min Act: -0.0003

Data Index: 288840 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0668. Min Act: -0.0003

Data Index: 410399 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1237125 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0677. Min Act: -0.0003

Data Index: 83611 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1348887 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0669. Min Act: -0.0003

Data Index: 461184 (C4 (Web Text))

Max Activating Token Index: 892