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

Dataset: The Pile

Neuron 3775 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: 1.0272. Min Range: -1.0272

Max Act: 1.0272. Min Act: -0.0000

Data Index: 989388 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1478943 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1087561 (The Pile)

Max Activating Token Index: 75

Text #3

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8404. Min Act: -0.0000

Data Index: 849427 (The Pile)

Max Activating Token Index: 857

Text #4

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7996. Min Act: -0.0000

Data Index: 909736 (The Pile)

Max Activating Token Index: 1018

Text #5

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1837441 (The Pile)

Max Activating Token Index: 242

Text #6

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1864143 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1471812 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1842063 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7013. Min Act: -0.0000

Data Index: 782805 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7177. Min Act: -0.0000

Data Index: 632324 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7728. Min Act: -0.0000

Data Index: 738106 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7763. Min Act: -0.0000

Data Index: 407189 (The Pile)

Max Activating Token Index: 413

Text #13

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1102039 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6806. Min Act: -0.0000

Data Index: 251016 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1942413 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7066. Min Act: -0.0000

Data Index: 75489 (The Pile)

Max Activating Token Index: 976

Text #17

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7109. Min Act: -0.0000

Data Index: 628010 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1200085 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6890. Min Act: -0.0000

Data Index: 697027 (The Pile)

Max Activating Token Index: 496