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

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

Neuron 428 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: 0.0877. Min Range: -0.0877

Max Act: 0.0877. Min Act: -0.0004

Data Index: 1157495 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0859. Min Act: -0.0002

Data Index: 532576 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0854. Min Act: -0.0003

Data Index: 299167 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0798. Min Act: -0.0002

Data Index: 290578 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0755. Min Act: -0.0003

Data Index: 193154 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0727. Min Act: -0.0003

Data Index: 362592 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0744. Min Act: -0.0003

Data Index: 885436 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0720. Min Act: -0.0003

Data Index: 1036169 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0693. Min Act: -0.0003

Data Index: 986798 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0710. Min Act: -0.0003

Data Index: 75185 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0677. Min Act: -0.0004

Data Index: 860214 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0692. Min Act: -0.0003

Data Index: 201304 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0690. Min Act: -0.0003

Data Index: 540326 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0693. Min Act: -0.0003

Data Index: 967053 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0680. Min Act: -0.0002

Data Index: 234561 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0661. Min Act: -0.0002

Data Index: 661042 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0675. Min Act: -0.0003

Data Index: 518276 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0693. Min Act: -0.0003

Data Index: 528036 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0669. Min Act: -0.0002

Data Index: 790642 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0657. Min Act: -0.0003

Data Index: 183120 (C4 (Web Text))

Max Activating Token Index: 331