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

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

Neuron 2099 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.8849. Min Act: -0.0000

Data Index: 224720 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.3499. Min Act: -0.0000

Data Index: 878916 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.5485. Min Act: -0.0000

Data Index: 1394895 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.4370. Min Act: -0.0000

Data Index: 1254094 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.4003. Min Act: -0.0000

Data Index: 583620 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.2890. Min Act: -0.0000

Data Index: 715491 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.3335. Min Act: -0.0000

Data Index: 173428 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.4516. Min Act: -0.0000

Data Index: 75308 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1108870 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1144655 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.2619. Min Act: -0.0000

Data Index: 710859 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.0893. Min Act: -0.0000

Data Index: 970055 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.1465. Min Act: -0.0000

Data Index: 610473 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.2538. Min Act: -0.0000

Data Index: 656165 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 1.8849. Min Range: -1.8849

Max Act: 0.9730. Min Act: -0.0000

Data Index: 647020 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.0441. Min Act: -0.0000

Data Index: 666035 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1332027 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 1.8849. Min Range: -1.8849

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1095979 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1331595 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 1.8849. Min Range: -1.8849

Max Act: 1.0679. Min Act: -0.0000

Data Index: 458980 (C4 (Web Text))

Max Activating Token Index: 906