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

Dataset: The Pile

Neuron 2079 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: 1.2616. Min Range: -1.2616

Max Act: 1.2616. Min Act: -0.0000

Data Index: 107285 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 1.2616. Min Range: -1.2616

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1142447 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 1.2616. Min Range: -1.2616

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1289425 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 1.2616. Min Range: -1.2616

Max Act: 1.1465. Min Act: -0.0000

Data Index: 1349928 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 1.2616. Min Range: -1.2616

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1391484 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 1.2616. Min Range: -1.2616

Max Act: 1.0197. Min Act: -0.0000

Data Index: 273977 (The Pile)

Max Activating Token Index: 419

Text #6

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9907. Min Act: -0.0000

Data Index: 826170 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 1.2616. Min Range: -1.2616

Max Act: 1.1048. Min Act: -0.0000

Data Index: 456802 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 1.2616. Min Range: -1.2616

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1270368 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1716524 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 1.2616. Min Range: -1.2616

Max Act: 1.0007. Min Act: -0.0000

Data Index: 578080 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.8625. Min Act: -0.0000

Data Index: 444160 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1711878 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1452528 (The Pile)

Max Activating Token Index: 937

Text #14

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1228397 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9348. Min Act: -0.0000

Data Index: 691871 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9849. Min Act: -0.0000

Data Index: 14703 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9198. Min Act: -0.0000

Data Index: 627487 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9230. Min Act: -0.0000

Data Index: 110714 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9484. Min Act: -0.0000

Data Index: 847578 (The Pile)

Max Activating Token Index: 116