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

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

Neuron 2417 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0905. Min Act: -0.0003

Data Index: 340427 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0875. Min Act: -0.0003

Data Index: 874652 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0822. Min Act: -0.0003

Data Index: 578487 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0738. Min Act: -0.0003

Data Index: 25719 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0831. Min Act: -0.0003

Data Index: 348885 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0791. Min Act: -0.0003

Data Index: 449648 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0808. Min Act: -0.0003

Data Index: 1132803 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1056085 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0810. Min Act: -0.0003

Data Index: 222816 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0777. Min Act: -0.0003

Data Index: 278023 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1298670 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0769. Min Act: -0.0003

Data Index: 1167341 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0771. Min Act: -0.0003

Data Index: 1046782 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0711. Min Act: -0.0003

Data Index: 343784 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0795. Min Act: -0.0003

Data Index: 468043 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0726. Min Act: -0.0003

Data Index: 729631 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0689. Min Act: -0.0003

Data Index: 210831 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1034137 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0761. Min Act: -0.0003

Data Index: 941072 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0759. Min Act: -0.0003

Data Index: 519508 (C4 (Web Text))

Max Activating Token Index: 822