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

Dataset: The Pile

Neuron 1675 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: 1.9768. Min Range: -1.9768

Max Act: 1.9768. Min Act: -0.0000

Data Index: 700473 (The Pile)

Max Activating Token Index: 869

Text #1

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1614311 (The Pile)

Max Activating Token Index: 701

Text #2

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2793. Min Act: -0.0000

Data Index: 1793002 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.4082. Min Act: -0.0000

Data Index: 1410685 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1218660 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2951. Min Act: -0.0000

Data Index: 749052 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.5135. Min Act: -0.0000

Data Index: 940600 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2196. Min Act: -0.0000

Data Index: 1146536 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1950478 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1219489 (The Pile)

Max Activating Token Index: 771

Text #10

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2769. Min Act: -0.0000

Data Index: 61272 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1914. Min Act: -0.0000

Data Index: 315010 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1746. Min Act: -0.0000

Data Index: 536907 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1337. Min Act: -0.0000

Data Index: 795315 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3245. Min Act: -0.0000

Data Index: 438088 (The Pile)

Max Activating Token Index: 858

Text #15

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2362. Min Act: -0.0000

Data Index: 1516056 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2309. Min Act: -0.0000

Data Index: 315983 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1747360 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1036735 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1322304 (The Pile)

Max Activating Token Index: 779