Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2773 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0954. Min Range: -1.0954

Max Act: 1.0954. Min Act: -0.0000

Data Index: 996410 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.9348. Min Act: -0.0000

Data Index: 673697 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1441735 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.9313. Min Act: -0.0000

Data Index: 994948 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1682364 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1603788 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.8116. Min Act: -0.0001

Data Index: 900088 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.8584. Min Act: -0.0000

Data Index: 796052 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7692. Min Act: -0.0000

Data Index: 800737 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.8751. Min Act: -0.0000

Data Index: 648269 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1281051 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.8071. Min Act: -0.0000

Data Index: 283227 (The Pile)

Max Activating Token Index: 819

Text #12

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1557376 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1529543 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1778472 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1208824 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7572. Min Act: -0.0000

Data Index: 625880 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7180. Min Act: -0.0000

Data Index: 391832 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1976294 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.0954. Min Range: -1.0954

Max Act: 0.6092. Min Act: -0.0001

Data Index: 1674219 (The Pile)

Max Activating Token Index: 411