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

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

Neuron 4448 in Layer 1

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: 0.0954. Min Range: -0.0954

Max Act: 0.0954. Min Act: -0.0003

Data Index: 206600 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1182525 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0848. Min Act: -0.0002

Data Index: 996872 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0827. Min Act: -0.0002

Data Index: 893902 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0823. Min Act: -0.0003

Data Index: 243646 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0826. Min Act: -0.0002

Data Index: 956270 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0815. Min Act: -0.0003

Data Index: 295500 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0824. Min Act: -0.0002

Data Index: 265699 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0794. Min Act: -0.0002

Data Index: 213699 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0809. Min Act: -0.0003

Data Index: 19801 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0797. Min Act: -0.0003

Data Index: 714715 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0795. Min Act: -0.0002

Data Index: 995289 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0798. Min Act: -0.0002

Data Index: 149644 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0792. Min Act: -0.0003

Data Index: 83280 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0775. Min Act: -0.0003

Data Index: 675727 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1302803 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0797. Min Act: -0.0003

Data Index: 957133 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0788. Min Act: -0.0002

Data Index: 587584 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1028528 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1357402 (C4 (Web Text))

Max Activating Token Index: 288