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

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

Neuron 3751 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1143671 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0539. Min Act: -0.0002

Data Index: 71273 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0475. Min Act: -0.0002

Data Index: 728602 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0475. Min Act: -0.0002

Data Index: 549409 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0465. Min Act: -0.0002

Data Index: 74840 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0492. Min Act: -0.0002

Data Index: 612498 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1214031 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0454. Min Act: -0.0002

Data Index: 119604 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0453. Min Act: -0.0002

Data Index: 80598 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0451. Min Act: -0.0002

Data Index: 225845 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0434. Min Act: -0.0002

Data Index: 904583 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0428. Min Act: -0.0002

Data Index: 508769 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0428. Min Act: -0.0002

Data Index: 372827 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1340487 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0420. Min Act: -0.0002

Data Index: 823589 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1315293 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0415. Min Act: -0.0002

Data Index: 331155 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1346126 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0414. Min Act: -0.0002

Data Index: 904467 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0420. Min Act: -0.0002

Data Index: 668868 (C4 (Web Text))

Max Activating Token Index: 287