Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 5 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1279448 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0759. Min Act: -0.0002

Data Index: 600588 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0647. Min Act: -0.0002

Data Index: 114079 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0635. Min Act: -0.0001

Data Index: 674114 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0575. Min Act: -0.0001

Data Index: 407667 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1354375 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0596. Min Act: -0.0001

Data Index: 281895 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0585. Min Act: -0.0001

Data Index: 975277 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1532899 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1575545 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0589. Min Act: -0.0001

Data Index: 781999 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0538. Min Act: -0.0002

Data Index: 968412 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0532. Min Act: -0.0001

Data Index: 82345 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0506. Min Act: -0.0001

Data Index: 191560 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0492. Min Act: -0.0001

Data Index: 152782 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0511. Min Act: -0.0001

Data Index: 426012 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0487. Min Act: -0.0001

Data Index: 506679 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0527. Min Act: -0.0002

Data Index: 207203 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1089917 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1623905 (Python Code)

Max Activating Token Index: 284