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

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

Neuron 2950 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1485328 (Python Code)

Max Activating Token Index: 849

Text #1

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1529491 (Python Code)

Max Activating Token Index: 363

Text #2

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1524268 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1566136 (Python Code)

Max Activating Token Index: 854

Text #4

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1421827 (Python Code)

Max Activating Token Index: 732

Text #5

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1442445 (Python Code)

Max Activating Token Index: 683

Text #6

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1336874 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1421728 (Python Code)

Max Activating Token Index: 766

Text #8

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1546801 (Python Code)

Max Activating Token Index: 718

Text #9

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1447417 (Python Code)

Max Activating Token Index: 490

Text #10

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1483395 (Python Code)

Max Activating Token Index: 263

Text #11

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6482. Min Act: -0.0000

Data Index: 704550 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1363127 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1590244 (Python Code)

Max Activating Token Index: 369

Text #14

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1501436 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1645590 (Python Code)

Max Activating Token Index: 405

Text #16

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1592041 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1545091 (Python Code)

Max Activating Token Index: 837

Text #18

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1622869 (Python Code)

Max Activating Token Index: 936

Text #19

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1617576 (Python Code)

Max Activating Token Index: 789