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

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

Neuron 1668 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1427226 (Python Code)

Max Activating Token Index: 250

Text #1

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1571441 (Python Code)

Max Activating Token Index: 926

Text #2

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2887. Min Act: -0.0000

Data Index: 1484388 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2249. Min Act: -0.0000

Data Index: 1374191 (Python Code)

Max Activating Token Index: 927

Text #4

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1536013 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2379. Min Act: -0.0000

Data Index: 1451766 (Python Code)

Max Activating Token Index: 577

Text #6

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1429131 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1945. Min Act: -0.0000

Data Index: 1451386 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1540881 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1578810 (Python Code)

Max Activating Token Index: 416

Text #10

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0658. Min Act: -0.0000

Data Index: 1435028 (Python Code)

Max Activating Token Index: 671

Text #11

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1557710 (Python Code)

Max Activating Token Index: 228

Text #12

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1457574 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1416049 (Python Code)

Max Activating Token Index: 209

Text #14

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1490886 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1637398 (Python Code)

Max Activating Token Index: 758

Text #16

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1500088 (Python Code)

Max Activating Token Index: 633

Text #17

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1545098 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1615553 (Python Code)

Max Activating Token Index: 426

Text #19

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1577650 (Python Code)

Max Activating Token Index: 573