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

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

Neuron 1002 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: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0002

Data Index: 756801 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0640. Min Act: -0.0002

Data Index: 428742 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0628. Min Act: -0.0002

Data Index: 204124 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0615. Min Act: -0.0001

Data Index: 351668 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0618. Min Act: -0.0002

Data Index: 154638 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0584. Min Act: -0.0002

Data Index: 722368 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0607. Min Act: -0.0002

Data Index: 191685 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0552. Min Act: -0.0002

Data Index: 991745 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0563. Min Act: -0.0002

Data Index: 865105 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1016719 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0564. Min Act: -0.0001

Data Index: 844661 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1207903 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1047907 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0553. Min Act: -0.0002

Data Index: 709302 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0558. Min Act: -0.0001

Data Index: 522690 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0539. Min Act: -0.0002

Data Index: 668757 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0541. Min Act: -0.0002

Data Index: 838759 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0558. Min Act: -0.0001

Data Index: 953974 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0497. Min Act: -0.0002

Data Index: 177318 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0548. Min Act: -0.0002

Data Index: 67392 (C4 (Web Text))

Max Activating Token Index: 479