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

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

Neuron 893 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: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1165291 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0634. Min Act: -0.0002

Data Index: 988409 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0618. Min Act: 0.0001

Data Index: 1307483 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0610. Min Act: -0.0002

Data Index: 382342 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0604. Min Act: -0.0002

Data Index: 2995 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0587. Min Act: -0.0002

Data Index: 367699 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1020383 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0585. Min Act: -0.0002

Data Index: 556553 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0575. Min Act: -0.0002

Data Index: 709124 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0560. Min Act: 0.0002

Data Index: 314764 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0563. Min Act: -0.0001

Data Index: 491612 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0571. Min Act: -0.0002

Data Index: 768527 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0556. Min Act: -0.0001

Data Index: 171547 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0567. Min Act: -0.0001

Data Index: 353861 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0550. Min Act: -0.0001

Data Index: 216862 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1047651 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0554. Min Act: -0.0001

Data Index: 41902 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0535. Min Act: 0.0000

Data Index: 388737 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0542. Min Act: -0.0002

Data Index: 594970 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0545. Min Act: -0.0001

Data Index: 398190 (C4 (Web Text))

Max Activating Token Index: 282