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

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

Neuron 1490 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: 0.3695. Min Range: -0.3695

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1593486 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1457187 (Python Code)

Max Activating Token Index: 239

Text #2

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1458790 (Python Code)

Max Activating Token Index: 899

Text #3

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1529309 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1593415 (Python Code)

Max Activating Token Index: 982

Text #5

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2428. Min Act: -0.0000

Data Index: 447140 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2369. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1385551 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2025. Min Act: -0.0000

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1396115 (Python Code)

Max Activating Token Index: 737

Text #10

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.1997. Min Act: -0.0000

Data Index: 692762 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2138. Min Act: -0.0000

Data Index: 799535 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2006. Min Act: -0.0000

Data Index: 775609 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1641154 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1430939 (Python Code)

Max Activating Token Index: 867

Text #15

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1466649 (Python Code)

Max Activating Token Index: 359

Text #16

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.1573. Min Act: -0.0000

Data Index: 569119 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1639855 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.1635. Min Act: -0.0000

Data Index: 474440 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.1586. Min Act: -0.0000

Data Index: 560892 (C4 (Web Text))

Max Activating Token Index: 559