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

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

Neuron 679 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.6061. Min Act: -0.0000

Data Index: 314225 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.6012. Min Act: -0.0000

Data Index: 1210490 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.1720. Min Act: -0.0000

Data Index: 101746 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0739. Min Act: -0.0000

Data Index: 355526 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9737. Min Act: -0.0000

Data Index: 930971 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9580. Min Act: -0.0000

Data Index: 688843 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0914. Min Act: -0.0000

Data Index: 711991 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1210119 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0465. Min Act: -0.0000

Data Index: 791102 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0147. Min Act: -0.0000

Data Index: 8065 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0218. Min Act: -0.0000

Data Index: 650860 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0073. Min Act: -0.0000

Data Index: 184419 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1220188 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9352. Min Act: -0.0000

Data Index: 173090 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1170247 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9554. Min Act: -0.0000

Data Index: 898251 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1029179 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1024571 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9035. Min Act: -0.0000

Data Index: 778739 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 1.6061. Min Range: -1.6061

Max Act: 0.9488. Min Act: -0.0000

Data Index: 515857 (C4 (Web Text))

Max Activating Token Index: 508