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

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

Neuron 446 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.9782. Min Act: -0.0000

Data Index: 1652133 (Python Code)

Max Activating Token Index: 372

Text #1

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6824. Min Act: -0.0000

Data Index: 1600471 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6341. Min Act: -0.0000

Data Index: 1528773 (Python Code)

Max Activating Token Index: 538

Text #3

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5557. Min Act: -0.0000

Data Index: 1466103 (Python Code)

Max Activating Token Index: 402

Text #4

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5897. Min Act: -0.0000

Data Index: 1403379 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5517. Min Act: -0.0000

Data Index: 1537302 (Python Code)

Max Activating Token Index: 706

Text #6

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.4727. Min Act: -0.0000

Data Index: 1627774 (Python Code)

Max Activating Token Index: 296

Text #7

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.3254. Min Act: -0.0000

Data Index: 1635199 (Python Code)

Max Activating Token Index: 408

Text #8

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1411906 (Python Code)

Max Activating Token Index: 639

Text #9

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1535627 (Python Code)

Max Activating Token Index: 440

Text #10

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1531444 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1526595 (Python Code)

Max Activating Token Index: 907

Text #12

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1475896 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2690. Min Act: -0.0000

Data Index: 1492477 (Python Code)

Max Activating Token Index: 358

Text #14

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1425341 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1641082 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1573185 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1539739 (Python Code)

Max Activating Token Index: 953

Text #18

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2029. Min Act: -0.0000

Data Index: 1484520 (Python Code)

Max Activating Token Index: 265

Text #19

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.1615. Min Act: -0.0000

Data Index: 1600234 (Python Code)

Max Activating Token Index: 492