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

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

Neuron 1695 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.7655. Min Act: -0.0000

Data Index: 1474122 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8621. Min Act: -0.0000

Data Index: 1389973 (Python Code)

Max Activating Token Index: 330

Text #2

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1392499 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.6814. Min Act: -0.0000

Data Index: 1639076 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.6558. Min Act: -0.0000

Data Index: 1467802 (Python Code)

Max Activating Token Index: 553

Text #5

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5543. Min Act: -0.0000

Data Index: 1537668 (Python Code)

Max Activating Token Index: 612

Text #6

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5940. Min Act: -0.0000

Data Index: 1603683 (Python Code)

Max Activating Token Index: 574

Text #7

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5319. Min Act: -0.0000

Data Index: 1514640 (Python Code)

Max Activating Token Index: 220

Text #8

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.7659. Min Act: -0.0000

Data Index: 1394816 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5268. Min Act: -0.0000

Data Index: 1526529 (Python Code)

Max Activating Token Index: 974

Text #10

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.4404. Min Act: -0.0000

Data Index: 1626806 (Python Code)

Max Activating Token Index: 307

Text #11

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.4365. Min Act: -0.0000

Data Index: 1473756 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5208. Min Act: -0.0000

Data Index: 1470498 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.6056. Min Act: -0.0000

Data Index: 1608633 (Python Code)

Max Activating Token Index: 588

Text #14

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.6236. Min Act: -0.0000

Data Index: 1423529 (Python Code)

Max Activating Token Index: 776

Text #15

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1640867 (Python Code)

Max Activating Token Index: 517

Text #16

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5414. Min Act: -0.0000

Data Index: 1570076 (Python Code)

Max Activating Token Index: 852

Text #17

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.6145. Min Act: -0.0000

Data Index: 1566827 (Python Code)

Max Activating Token Index: 660

Text #18

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1631700 (Python Code)

Max Activating Token Index: 480

Text #19

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.4801. Min Act: -0.0000

Data Index: 1383082 (Python Code)

Max Activating Token Index: 630