Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2247 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0757. Min Act: -0.0001

Data Index: 615426 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0778. Min Act: -0.0001

Data Index: 658910 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0001

Data Index: 737317 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1250256 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1349625 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1320699 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0700. Min Act: -0.0001

Data Index: 859540 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0722. Min Act: -0.0001

Data Index: 894351 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1010393 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1016837 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0713. Min Act: -0.0001

Data Index: 83401 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0733. Min Act: -0.0001

Data Index: 876629 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0710. Min Act: -0.0001

Data Index: 418485 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0723. Min Act: -0.0001

Data Index: 289627 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1173255 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1340890 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1001166 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0734. Min Act: -0.0001

Data Index: 422450 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0697. Min Act: -0.0001

Data Index: 958831 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0741. Min Act: -0.0001

Data Index: 702797 (C4 (Web Text))

Max Activating Token Index: 911