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

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

Neuron 1714 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.4871. Min Act: -0.0000

Data Index: 282525 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6350. Min Act: -0.0000

Data Index: 297100 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.7348. Min Act: -0.0000

Data Index: 1276044 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.3465. Min Act: -0.0000

Data Index: 45664 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.3168. Min Act: -0.0000

Data Index: 954067 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.2750. Min Act: -0.0000

Data Index: 144439 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.2725. Min Act: -0.0000

Data Index: 369518 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.2562. Min Act: -0.0000

Data Index: 1254002 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.1954. Min Act: -0.0000

Data Index: 239551 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.3873. Min Act: -0.0000

Data Index: 454715 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.2623. Min Act: -0.0000

Data Index: 1142769 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.0823. Min Act: -0.0000

Data Index: 955316 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.0888. Min Act: -0.0000

Data Index: 770662 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.0746. Min Act: -0.0000

Data Index: 1018326 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 2.7348. Min Range: -2.7348

Max Act: 1.9384. Min Act: -0.0000

Data Index: 775929 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 2.7348. Min Range: -2.7348

Max Act: 1.8332. Min Act: -0.0000

Data Index: 174788 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.0027. Min Act: -0.0000

Data Index: 24029 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.0200. Min Act: -0.0000

Data Index: 935750 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 2.7348. Min Range: -2.7348

Max Act: 1.9829. Min Act: -0.0000

Data Index: 414295 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.0875. Min Act: -0.0000

Data Index: 1094603 (C4 (Web Text))

Max Activating Token Index: 812