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

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

Neuron 4935 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1449053 (Python Code)

Max Activating Token Index: 843

Text #1

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7764. Min Act: 0.0000

Data Index: 147047 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7214. Min Act: 0.0000

Data Index: 1480650 (Python Code)

Max Activating Token Index: 882

Text #3

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1544644 (Python Code)

Max Activating Token Index: 403

Text #4

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1525859 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1400615 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1466786 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1540023 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1534021 (Python Code)

Max Activating Token Index: 349

Text #9

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6449. Min Act: -0.0001

Data Index: 1363208 (Python Code)

Max Activating Token Index: 573

Text #10

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1527750 (Python Code)

Max Activating Token Index: 547

Text #11

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6427. Min Act: -0.0000

Data Index: 759036 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1453345 (Python Code)

Max Activating Token Index: 394

Text #13

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1549865 (Python Code)

Max Activating Token Index: 858

Text #14

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6185. Min Act: -0.0000

Data Index: 463889 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1629507 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6017. Min Act: 0.0000

Data Index: 333419 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1636547 (Python Code)

Max Activating Token Index: 645

Text #18

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1574012 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1375421 (Python Code)

Max Activating Token Index: 232