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

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

Neuron 1219 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1400942 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1627967 (Python Code)

Max Activating Token Index: 455

Text #2

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5409. Min Act: 0.0000

Data Index: 1404765 (Python Code)

Max Activating Token Index: 363

Text #3

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1425465 (Python Code)

Max Activating Token Index: 365

Text #4

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1475766 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1546941 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1533333 (Python Code)

Max Activating Token Index: 642

Text #7

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1391150 (Python Code)

Max Activating Token Index: 706

Text #8

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5026. Min Act: 0.0000

Data Index: 1646760 (Python Code)

Max Activating Token Index: 479

Text #9

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5226. Min Act: 0.0003

Data Index: 1630677 (Python Code)

Max Activating Token Index: 961

Text #10

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5326. Min Act: 0.0003

Data Index: 1536724 (Python Code)

Max Activating Token Index: 1021

Text #11

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1389039 (Python Code)

Max Activating Token Index: 675

Text #12

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1556786 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1480134 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5024. Min Act: 0.0001

Data Index: 1374592 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1404134 (Python Code)

Max Activating Token Index: 99

Text #16

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5025. Min Act: 0.0000

Data Index: 1511413 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1565659 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1434810 (Python Code)

Max Activating Token Index: 934

Text #19

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1382153 (Python Code)

Max Activating Token Index: 380