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

Dataset: The Pile

Neuron 1936 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: 1.1329. Min Range: -1.1329

Max Act: 1.0756. Min Act: -0.0000

Data Index: 991727 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 1.1329. Min Range: -1.1329

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1370729 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 1.1329. Min Range: -1.1329

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1558792 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 1.1329. Min Range: -1.1329

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1443596 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 1.1329. Min Range: -1.1329

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1687798 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.9873. Min Act: -0.0000

Data Index: 1371397 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1488608 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.9045. Min Act: -0.0000

Data Index: 819395 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1921121 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8728. Min Act: -0.0000

Data Index: 869031 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1257025 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8829. Min Act: -0.0000

Data Index: 109866 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1819163 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8710. Min Act: -0.0000

Data Index: 142431 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1199910 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1888671 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1005664 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1025267 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1648584 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1806250 (The Pile)

Max Activating Token Index: 852