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

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

Neuron 1597 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1495606 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2052. Min Act: -0.0000

Data Index: 184962 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1916. Min Act: -0.0001

Data Index: 292717 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1944. Min Act: -0.0000

Data Index: 723394 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1509148 (Python Code)

Max Activating Token Index: 362

Text #5

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1401077 (Python Code)

Max Activating Token Index: 203

Text #6

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1062238 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1239288 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1648. Min Act: -0.0000

Data Index: 925465 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1384291 (Python Code)

Max Activating Token Index: 946

Text #10

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1511215 (Python Code)

Max Activating Token Index: 786

Text #11

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1511058 (Python Code)

Max Activating Token Index: 601

Text #12

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1501823 (Python Code)

Max Activating Token Index: 227

Text #13

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1456730 (Python Code)

Max Activating Token Index: 664

Text #14

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1513417 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1610. Min Act: -0.0000

Data Index: 49578 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1433277 (Python Code)

Max Activating Token Index: 554

Text #17

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1442728 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1618796 (Python Code)

Max Activating Token Index: 472

Text #19

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1511148 (Python Code)

Max Activating Token Index: 496