Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3196 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1029157 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0647. Min Act: -0.0002

Data Index: 76224 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1049926 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0741. Min Act: -0.0002

Data Index: 528598 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0686. Min Act: -0.0002

Data Index: 704211 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1117930 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1145977 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0682. Min Act: -0.0002

Data Index: 526543 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0642. Min Act: -0.0002

Data Index: 329720 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0677. Min Act: -0.0002

Data Index: 498661 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1243984 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0720. Min Act: -0.0002

Data Index: 937491 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0709. Min Act: -0.0002

Data Index: 465606 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0688. Min Act: -0.0002

Data Index: 159276 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0658. Min Act: -0.0002

Data Index: 755880 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0631. Min Act: -0.0002

Data Index: 542115 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1358833 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0664. Min Act: -0.0002

Data Index: 313700 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1115419 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1159093 (C4 (Web Text))

Max Activating Token Index: 286