Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3705 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0871. Min Act: -0.0001

Data Index: 346145 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0848. Min Act: -0.0001

Data Index: 120266 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0809. Min Act: -0.0001

Data Index: 449802 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1084811 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0796. Min Act: -0.0001

Data Index: 90704 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0793. Min Act: -0.0001

Data Index: 456087 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1246529 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0787. Min Act: -0.0001

Data Index: 843008 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0787. Min Act: -0.0001

Data Index: 858964 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1147474 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1088314 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0782. Min Act: -0.0001

Data Index: 371252 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0772. Min Act: -0.0001

Data Index: 15044 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0777. Min Act: -0.0001

Data Index: 42724 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0778. Min Act: -0.0001

Data Index: 573037 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1246427 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1288812 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0757. Min Act: -0.0001

Data Index: 544922 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0757. Min Act: -0.0001

Data Index: 932401 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0768. Min Act: -0.0001

Data Index: 614917 (C4 (Web Text))

Max Activating Token Index: 721