Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5786. Min Act: -0.0001

Data Index: 31112 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5848. Min Act: -0.0001

Data Index: 646623 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4856. Min Act: -0.0001

Data Index: 1528167 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5038. Min Act: -0.0001

Data Index: 1515509 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4899. Min Act: -0.0000

Data Index: 678671 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4832. Min Act: -0.0001

Data Index: 1631280 (Python Code)

Max Activating Token Index: 50

Text #6

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4791. Min Act: -0.0001

Data Index: 884304 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4802. Min Act: -0.0001

Data Index: 1388272 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1638146 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4737. Min Act: -0.0001

Data Index: 1435269 (Python Code)

Max Activating Token Index: 787

Text #10

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4601. Min Act: -0.0001

Data Index: 1570069 (Python Code)

Max Activating Token Index: 556

Text #11

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4733. Min Act: -0.0001

Data Index: 1643217 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4551. Min Act: -0.0001

Data Index: 998775 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1500068 (Python Code)

Max Activating Token Index: 25

Text #14

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1636360 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4675. Min Act: -0.0001

Data Index: 1494273 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4617. Min Act: -0.0001

Data Index: 1414142 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4428. Min Act: -0.0001

Data Index: 1590851 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4392. Min Act: -0.0001

Data Index: 1616339 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4532. Min Act: -0.0001

Data Index: 1087368 (C4 (Web Text))

Max Activating Token Index: 849