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

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

Neuron 4003 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1378. Min Range: -3.1378

Max Act: 3.0936. Min Act: -0.0001

Data Index: 1431886 (Python Code)

Max Activating Token Index: 752

Text #1

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.8935. Min Act: -0.0001

Data Index: 1624967 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 3.1378. Min Range: -3.1378

Max Act: 3.1378. Min Act: -0.0000

Data Index: 1385002 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 3.1378. Min Range: -3.1378

Max Act: 3.0735. Min Act: -0.0001

Data Index: 1518076 (Python Code)

Max Activating Token Index: 607

Text #4

Max Range: 3.1378. Min Range: -3.1378

Max Act: 3.0823. Min Act: -0.0001

Data Index: 1388935 (Python Code)

Max Activating Token Index: 543

Text #5

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.8536. Min Act: -0.0001

Data Index: 1511238 (Python Code)

Max Activating Token Index: 455

Text #6

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.4641. Min Act: -0.0001

Data Index: 1625605 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.7568. Min Act: -0.0000

Data Index: 1598982 (Python Code)

Max Activating Token Index: 280

Text #8

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.8667. Min Act: -0.0001

Data Index: 1482285 (Python Code)

Max Activating Token Index: 960

Text #9

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.9800. Min Act: -0.0001

Data Index: 1410983 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.7377. Min Act: -0.0001

Data Index: 1440019 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.5684. Min Act: -0.0000

Data Index: 1399635 (Python Code)

Max Activating Token Index: 544

Text #12

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.6993. Min Act: -0.0001

Data Index: 1400262 (Python Code)

Max Activating Token Index: 580

Text #13

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.7806. Min Act: -0.0001

Data Index: 1440311 (Python Code)

Max Activating Token Index: 963

Text #14

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.6595. Min Act: -0.0001

Data Index: 1495176 (Python Code)

Max Activating Token Index: 260

Text #15

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.7399. Min Act: -0.0001

Data Index: 1426445 (Python Code)

Max Activating Token Index: 521

Text #16

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.7260. Min Act: -0.0000

Data Index: 1563203 (Python Code)

Max Activating Token Index: 447

Text #17

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.4974. Min Act: -0.0000

Data Index: 1631141 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.5948. Min Act: -0.0000

Data Index: 1497177 (Python Code)

Max Activating Token Index: 973

Text #19

Max Range: 3.1378. Min Range: -3.1378

Max Act: 2.5839. Min Act: -0.0001

Data Index: 1457807 (Python Code)

Max Activating Token Index: 875