Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1399 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.9330. Min Act: -0.0001

Data Index: 1423398 (Python Code)

Max Activating Token Index: 894

Text #1

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.9340. Min Act: -0.0001

Data Index: 1543573 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8619. Min Act: -0.0001

Data Index: 1477032 (Python Code)

Max Activating Token Index: 745

Text #3

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8671. Min Act: -0.0001

Data Index: 1380365 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8872. Min Act: -0.0001

Data Index: 1483633 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1638322 (Python Code)

Max Activating Token Index: 636

Text #6

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8415. Min Act: -0.0001

Data Index: 1630477 (Python Code)

Max Activating Token Index: 647

Text #7

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8259. Min Act: -0.0001

Data Index: 1653994 (Python Code)

Max Activating Token Index: 263

Text #8

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8213. Min Act: -0.0001

Data Index: 1435412 (Python Code)

Max Activating Token Index: 436

Text #9

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8612. Min Act: -0.0001

Data Index: 1597807 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8362. Min Act: -0.0001

Data Index: 1532779 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8294. Min Act: -0.0001

Data Index: 1596963 (Python Code)

Max Activating Token Index: 937

Text #12

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7684. Min Act: -0.0001

Data Index: 1615161 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7894. Min Act: -0.0001

Data Index: 1488780 (Python Code)

Max Activating Token Index: 329

Text #14

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7444. Min Act: -0.0001

Data Index: 1583079 (Python Code)

Max Activating Token Index: 897

Text #15

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7493. Min Act: -0.0001

Data Index: 1377300 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7431. Min Act: -0.0001

Data Index: 1365304 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7804. Min Act: -0.0001

Data Index: 1411210 (Python Code)

Max Activating Token Index: 934

Text #18

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7667. Min Act: -0.0001

Data Index: 1387933 (Python Code)

Max Activating Token Index: 50

Text #19

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7455. Min Act: -0.0001

Data Index: 1491375 (Python Code)

Max Activating Token Index: 823