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

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

Neuron 1616 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1770. Min Range: -2.1770

Max Act: 2.1770. Min Act: 0.0000

Data Index: 652452 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 2.1770. Min Range: -2.1770

Max Act: 2.1531. Min Act: 0.0000

Data Index: 147591 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 2.1770. Min Range: -2.1770

Max Act: 2.1215. Min Act: 0.0001

Data Index: 665748 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.8700. Min Act: -0.0000

Data Index: 317792 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.7012. Min Act: 0.0000

Data Index: 1266424 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.6710. Min Act: 0.0001

Data Index: 370103 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.6002. Min Act: 0.0000

Data Index: 481081 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.5532. Min Act: -0.0000

Data Index: 725610 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.4979. Min Act: -0.0000

Data Index: 418655 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1081023 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.3543. Min Act: -0.0000

Data Index: 987657 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.4007. Min Act: -0.0000

Data Index: 1312958 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1206732 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.2525. Min Act: -0.0000

Data Index: 288362 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.2200. Min Act: -0.0000

Data Index: 32338 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.1901. Min Act: 0.0002

Data Index: 1178216 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.0879. Min Act: 0.0000

Data Index: 681834 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.1527. Min Act: 0.0000

Data Index: 1226648 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.1511. Min Act: 0.0000

Data Index: 1296883 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 2.1770. Min Range: -2.1770

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1223273 (C4 (Web Text))

Max Activating Token Index: 564