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

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

Neuron 1977 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1268093 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0000

Data Index: 959405 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0789. Min Act: -0.0000

Data Index: 742198 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1074687 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0742. Min Act: -0.0000

Data Index: 634900 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0647. Min Act: -0.0000

Data Index: 723937 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0698. Min Act: -0.0000

Data Index: 806174 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1087642 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0672. Min Act: -0.0000

Data Index: 418833 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0639. Min Act: -0.0000

Data Index: 904714 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0617. Min Act: -0.0000

Data Index: 818029 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0621. Min Act: -0.0000

Data Index: 991132 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0614. Min Act: -0.0000

Data Index: 946394 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0607. Min Act: -0.0000

Data Index: 340922 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1261453 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0624. Min Act: -0.0000

Data Index: 765979 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1303578 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0621. Min Act: -0.0000

Data Index: 552775 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0582. Min Act: -0.0000

Data Index: 43400 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0605. Min Act: -0.0000

Data Index: 211900 (C4 (Web Text))

Max Activating Token Index: 783