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

Dataset: The Pile

Neuron 3040 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.8742. Min Act: -0.0000

Data Index: 1335470 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.7740. Min Act: -0.0000

Data Index: 1598806 (The Pile)

Max Activating Token Index: 983

Text #2

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.6599. Min Act: -0.0000

Data Index: 206405 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.7445. Min Act: -0.0000

Data Index: 531896 (The Pile)

Max Activating Token Index: 683

Text #4

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.5426. Min Act: -0.0000

Data Index: 969661 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1286922 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.3888. Min Act: -0.0000

Data Index: 532023 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.4079. Min Act: 0.0000

Data Index: 851842 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1210946 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.4184. Min Act: 0.0000

Data Index: 1268553 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.3368. Min Act: -0.0000

Data Index: 522740 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1301422 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1141472 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1563499 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.2737. Min Act: -0.0000

Data Index: 126865 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1083905 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.1949. Min Act: -0.0000

Data Index: 257044 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.1852. Min Act: -0.0000

Data Index: 967087 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.1746. Min Act: 0.0000

Data Index: 528146 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1392285 (The Pile)

Max Activating Token Index: 100