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

Dataset: The Pile

Neuron 1621 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.4998. Min Act: -0.0000

Data Index: 7188 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.1804. Min Act: -0.0000

Data Index: 941823 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1314817 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1710134 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.1065. Min Act: -0.0000

Data Index: 411158 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1013241 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.0380. Min Act: -0.0000

Data Index: 41873 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1293949 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.0077. Min Act: -0.0000

Data Index: 769970 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9857. Min Act: -0.0000

Data Index: 791792 (The Pile)

Max Activating Token Index: 183

Text #10

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9846. Min Act: -0.0000

Data Index: 153596 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1078381 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9327. Min Act: -0.0000

Data Index: 680070 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1359716 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1228527 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.8687. Min Act: -0.0000

Data Index: 502611 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9012. Min Act: -0.0000

Data Index: 809506 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1739833 (The Pile)

Max Activating Token Index: 445

Text #18

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.8961. Min Act: -0.0000

Data Index: 37402 (The Pile)

Max Activating Token Index: 973

Text #19

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9149. Min Act: -0.0000

Data Index: 325079 (The Pile)

Max Activating Token Index: 898