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

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

Neuron 578 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0706. Min Act: -0.0005

Data Index: 170175 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0688. Min Act: -0.0005

Data Index: 1234709 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0693. Min Act: -0.0005

Data Index: 320564 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0649. Min Act: -0.0005

Data Index: 534403 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0657. Min Act: -0.0005

Data Index: 917497 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0668. Min Act: -0.0005

Data Index: 341098 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0641. Min Act: -0.0005

Data Index: 146656 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0664. Min Act: -0.0005

Data Index: 644201 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0676. Min Act: -0.0005

Data Index: 1355398 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0662. Min Act: -0.0005

Data Index: 586657 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0654. Min Act: -0.0005

Data Index: 411907 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0657. Min Act: -0.0005

Data Index: 981748 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0653. Min Act: -0.0005

Data Index: 522537 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0642. Min Act: -0.0005

Data Index: 333387 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0612. Min Act: -0.0005

Data Index: 1003529 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0611. Min Act: -0.0005

Data Index: 348687 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0585. Min Act: -0.0005

Data Index: 1232885 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0604. Min Act: -0.0005

Data Index: 758462 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0603. Min Act: -0.0005

Data Index: 1035114 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0619. Min Act: -0.0005

Data Index: 217210 (C4 (Web Text))

Max Activating Token Index: 725