Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 162 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.5196. Min Act: -0.0000

Data Index: 170355 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.5180. Min Act: -0.0000

Data Index: 705504 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1132419 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.1544. Min Act: -0.0000

Data Index: 481985 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.1319. Min Act: -0.0000

Data Index: 830660 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.0631. Min Act: -0.0000

Data Index: 62459 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.0743. Min Act: -0.0000

Data Index: 256315 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.0514. Min Act: -0.0000

Data Index: 190532 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1056225 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9389. Min Act: -0.0000

Data Index: 471471 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8943. Min Act: -0.0000

Data Index: 743756 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8541. Min Act: -0.0000

Data Index: 865294 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8717. Min Act: -0.0000

Data Index: 635897 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7620. Min Act: -0.0000

Data Index: 586605 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8427. Min Act: -0.0000

Data Index: 833068 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8214. Min Act: -0.0000

Data Index: 544008 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8076. Min Act: -0.0000

Data Index: 297922 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7917. Min Act: -0.0000

Data Index: 411137 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7696. Min Act: -0.0000

Data Index: 911819 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7823. Min Act: -0.0000

Data Index: 787491 (C4 (Web Text))

Max Activating Token Index: 493