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

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

Neuron 620 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: 0.0799. Min Range: -0.0799

Max Act: 0.0799. Min Act: -0.0005

Data Index: 1300803 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0763. Min Act: -0.0005

Data Index: 209604 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0744. Min Act: -0.0005

Data Index: 989295 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0746. Min Act: -0.0005

Data Index: 1330059 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0730. Min Act: -0.0005

Data Index: 112904 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0783. Min Act: -0.0005

Data Index: 449881 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0714. Min Act: -0.0005

Data Index: 871303 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0717. Min Act: -0.0005

Data Index: 938056 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0730. Min Act: -0.0005

Data Index: 1155058 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0701. Min Act: -0.0005

Data Index: 706470 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0671. Min Act: -0.0005

Data Index: 707504 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0689. Min Act: -0.0005

Data Index: 69435 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0701. Min Act: -0.0005

Data Index: 1040245 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0629. Min Act: -0.0005

Data Index: 467903 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0629. Min Act: -0.0005

Data Index: 655381 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0716. Min Act: -0.0005

Data Index: 456191 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0678. Min Act: -0.0005

Data Index: 164430 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0630. Min Act: -0.0005

Data Index: 550201 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0647. Min Act: -0.0005

Data Index: 575968 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0656. Min Act: -0.0005

Data Index: 519539 (C4 (Web Text))

Max Activating Token Index: 528