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

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

Neuron 2692 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1425423 (Python Code)

Max Activating Token Index: 719

Text #1

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1567183 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1366497 (Python Code)

Max Activating Token Index: 456

Text #3

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1486763 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1646282 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1504851 (Python Code)

Max Activating Token Index: 857

Text #6

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1557374 (Python Code)

Max Activating Token Index: 778

Text #7

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1417072 (Python Code)

Max Activating Token Index: 480

Text #8

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1496133 (Python Code)

Max Activating Token Index: 939

Text #9

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1516944 (Python Code)

Max Activating Token Index: 519

Text #10

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1477332 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1559952 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.3865. Min Act: -0.0001

Data Index: 1480096 (Python Code)

Max Activating Token Index: 814

Text #13

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1541307 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1378440 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1484262 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1491825 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1600114 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1564849 (Python Code)

Max Activating Token Index: 612

Text #19

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1377120 (Python Code)

Max Activating Token Index: 1012