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

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

Neuron 181 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1166204 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0702. Min Act: -0.0002

Data Index: 122456 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0631. Min Act: -0.0002

Data Index: 699046 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0656. Min Act: -0.0002

Data Index: 483777 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0652. Min Act: -0.0002

Data Index: 574245 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0629. Min Act: -0.0002

Data Index: 4976 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0606. Min Act: -0.0002

Data Index: 371060 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0624. Min Act: -0.0002

Data Index: 427762 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0582. Min Act: -0.0001

Data Index: 443750 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0581. Min Act: -0.0002

Data Index: 220598 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1288022 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0656. Min Act: -0.0002

Data Index: 119738 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0595. Min Act: -0.0002

Data Index: 483977 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0596. Min Act: -0.0001

Data Index: 645561 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1325946 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0611. Min Act: -0.0001

Data Index: 741766 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1037716 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0596. Min Act: -0.0002

Data Index: 203431 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0576. Min Act: -0.0002

Data Index: 920048 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0588. Min Act: -0.0001

Data Index: 17715 (C4 (Web Text))

Max Activating Token Index: 30