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

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

Neuron 873 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.9503. Min Act: -0.0000

Data Index: 472451 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1571817 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1519774 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8853. Min Act: -0.0000

Data Index: 347987 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1163665 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8341. Min Act: -0.0000

Data Index: 430760 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1434203 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8008. Min Act: -0.0000

Data Index: 600196 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8615. Min Act: -0.0000

Data Index: 431671 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1656434 (Python Code)

Max Activating Token Index: 815

Text #10

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1421801 (Python Code)

Max Activating Token Index: 910

Text #11

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1555480 (Python Code)

Max Activating Token Index: 823

Text #12

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1517608 (Python Code)

Max Activating Token Index: 459

Text #13

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1557621 (Python Code)

Max Activating Token Index: 266

Text #14

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1473932 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1456509 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1434879 (Python Code)

Max Activating Token Index: 320

Text #17

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1601558 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1511734 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 0.9503. Min Range: -0.9503

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1572227 (Python Code)

Max Activating Token Index: 88