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

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

Neuron 3071 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.6950. Min Act: -0.0000

Data Index: 1454198 (Python Code)

Max Activating Token Index: 260

Text #1

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.8161. Min Act: -0.0000

Data Index: 1434970 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.4404. Min Act: -0.0000

Data Index: 1435199 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.1376. Min Act: -0.0000

Data Index: 1552488 (Python Code)

Max Activating Token Index: 87

Text #4

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.5391. Min Act: -0.0000

Data Index: 1422558 (Python Code)

Max Activating Token Index: 541

Text #5

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.3504. Min Act: -0.0001

Data Index: 1482182 (Python Code)

Max Activating Token Index: 504

Text #6

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.0971. Min Act: -0.0001

Data Index: 1625727 (Python Code)

Max Activating Token Index: 558

Text #7

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.2970. Min Act: -0.0001

Data Index: 1627306 (Python Code)

Max Activating Token Index: 687

Text #8

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.0316. Min Act: -0.0001

Data Index: 1479612 (Python Code)

Max Activating Token Index: 351

Text #9

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.0108. Min Act: -0.0000

Data Index: 1637189 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.0289. Min Act: -0.0001

Data Index: 1607196 (Python Code)

Max Activating Token Index: 423

Text #11

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.8622. Min Act: -0.0000

Data Index: 1508299 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.9941. Min Act: -0.0000

Data Index: 1437633 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.9850. Min Act: -0.0001

Data Index: 1548622 (Python Code)

Max Activating Token Index: 357

Text #14

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.1311. Min Act: -0.0000

Data Index: 1533110 (Python Code)

Max Activating Token Index: 349

Text #15

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.8430. Min Act: -0.0001

Data Index: 1649108 (Python Code)

Max Activating Token Index: 242

Text #16

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.1006. Min Act: -0.0001

Data Index: 1556206 (Python Code)

Max Activating Token Index: 775

Text #17

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.8574. Min Act: -0.0000

Data Index: 1384181 (Python Code)

Max Activating Token Index: 755

Text #18

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.0261. Min Act: -0.0000

Data Index: 1391040 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.0308. Min Act: -0.0000

Data Index: 1561631 (Python Code)

Max Activating Token Index: 20