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

Dataset: The Pile

Neuron 3661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.4670. Min Act: -0.0000

Data Index: 859742 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.4265. Min Act: -0.0000

Data Index: 660599 (The Pile)

Max Activating Token Index: 589

Text #2

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1743276 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.5588. Min Act: -0.0000

Data Index: 1065659 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.3611. Min Act: -0.0000

Data Index: 133652 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1322070 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.4104. Min Act: -0.0000

Data Index: 492395 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.4281. Min Act: -0.0000

Data Index: 364932 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.4112. Min Act: -0.0000

Data Index: 1926607 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2546. Min Act: -0.0000

Data Index: 1522190 (The Pile)

Max Activating Token Index: 955

Text #10

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2276. Min Act: -0.0000

Data Index: 394112 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.4049. Min Act: -0.0000

Data Index: 1365650 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1833863 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2363. Min Act: -0.0000

Data Index: 632255 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1039825 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1150610 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2627. Min Act: -0.0000

Data Index: 55189 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.1211. Min Act: -0.0000

Data Index: 811083 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1366128 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2818. Min Act: -0.0000

Data Index: 364557 (The Pile)

Max Activating Token Index: 638