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

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

Neuron 5086 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0715. Min Act: -0.0000

Data Index: 486554 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1152701 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0632. Min Act: -0.0000

Data Index: 69406 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1277633 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1592167 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0546. Min Act: -0.0000

Data Index: 636135 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1254167 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1139556 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0421. Min Act: -0.0000

Data Index: 856008 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1195526 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0458. Min Act: -0.0000

Data Index: 1486668 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0416. Min Act: -0.0000

Data Index: 866874 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0398. Min Act: -0.0000

Data Index: 702664 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0414. Min Act: -0.0000

Data Index: 879009 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0412. Min Act: -0.0001

Data Index: 77264 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0401. Min Act: -0.0000

Data Index: 310701 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0423. Min Act: -0.0000

Data Index: 54002 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0391. Min Act: -0.0000

Data Index: 820068 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1031974 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0378. Min Act: -0.0000

Data Index: 663054 (C4 (Web Text))

Max Activating Token Index: 600