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

Dataset: The Pile

Neuron 3850 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.7425. Min Act: -0.0000

Data Index: 525357 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4709. Min Act: -0.0000

Data Index: 199363 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4121. Min Act: -0.0000

Data Index: 730333 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4249. Min Act: -0.0000

Data Index: 142472 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1127876 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4109. Min Act: -0.0000

Data Index: 342918 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4309. Min Act: -0.0000

Data Index: 219874 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1081858 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1691361 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1692371 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1781979 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1541375 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1274386 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3717. Min Act: -0.0000

Data Index: 893069 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1620489 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3571. Min Act: -0.0000

Data Index: 802339 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1446501 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1499548 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1998249 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.3520. Min Act: -0.0000

Data Index: 113274 (The Pile)

Max Activating Token Index: 869