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

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

Neuron 1253 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0834. Min Act: -0.0003

Data Index: 631442 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0757. Min Act: -0.0003

Data Index: 1006973 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0760. Min Act: -0.0003

Data Index: 179619 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0718. Min Act: -0.0003

Data Index: 23741 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0714. Min Act: -0.0003

Data Index: 921851 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0707. Min Act: -0.0003

Data Index: 1201537 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0662. Min Act: -0.0003

Data Index: 880079 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0686. Min Act: -0.0003

Data Index: 1177292 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0670. Min Act: -0.0003

Data Index: 738845 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0677. Min Act: -0.0003

Data Index: 932604 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0642. Min Act: -0.0002

Data Index: 370370 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0635. Min Act: -0.0003

Data Index: 920819 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0648. Min Act: -0.0003

Data Index: 41433 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0627. Min Act: -0.0003

Data Index: 953252 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0612. Min Act: -0.0002

Data Index: 582610 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0622. Min Act: -0.0002

Data Index: 9921 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1194813 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0620. Min Act: -0.0003

Data Index: 693180 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0617. Min Act: -0.0003

Data Index: 48605 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1018469 (C4 (Web Text))

Max Activating Token Index: 495