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

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

Neuron 844 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: 2.5221. Min Range: -2.5221

Max Act: 2.5221. Min Act: -0.0000

Data Index: 840628 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1465927 (Python Code)

Max Activating Token Index: 449

Text #2

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2870. Min Act: -0.0000

Data Index: 1584697 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1648029 (Python Code)

Max Activating Token Index: 479

Text #4

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1391284 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1406107 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2710. Min Act: -0.0000

Data Index: 1504463 (Python Code)

Max Activating Token Index: 647

Text #7

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1614360 (Python Code)

Max Activating Token Index: 931

Text #8

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1556484 (Python Code)

Max Activating Token Index: 494

Text #9

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1404086 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2623. Min Act: -0.0000

Data Index: 564897 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2607. Min Act: -0.0000

Data Index: 1507469 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1592998 (Python Code)

Max Activating Token Index: 265

Text #13

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.3539. Min Act: -0.0000

Data Index: 1377001 (Python Code)

Max Activating Token Index: 730

Text #14

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1579768 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2495. Min Act: -0.0000

Data Index: 1646215 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1508512 (Python Code)

Max Activating Token Index: 223

Text #17

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.1583. Min Act: -0.0000

Data Index: 1549946 (Python Code)

Max Activating Token Index: 518

Text #18

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.1589. Min Act: -0.0000

Data Index: 1627690 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1392054 (Python Code)

Max Activating Token Index: 50