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

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

Neuron 3491 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2431. Min Act: -0.0002

Data Index: 1081677 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2218. Min Act: -0.0002

Data Index: 1126484 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2107. Min Act: -0.0002

Data Index: 342262 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1408. Min Act: -0.0002

Data Index: 980852 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1804. Min Act: -0.0002

Data Index: 648727 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1684. Min Act: -0.0002

Data Index: 780537 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1780. Min Act: -0.0002

Data Index: 209011 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1915. Min Act: -0.0002

Data Index: 668225 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1712. Min Act: -0.0002

Data Index: 1226375 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1508. Min Act: -0.0002

Data Index: 48933 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1626. Min Act: -0.0002

Data Index: 232407 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1608. Min Act: -0.0002

Data Index: 107731 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1666. Min Act: -0.0002

Data Index: 1350863 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1591. Min Act: -0.0002

Data Index: 814101 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1632. Min Act: -0.0002

Data Index: 665560 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1613. Min Act: -0.0002

Data Index: 1063810 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1704. Min Act: -0.0002

Data Index: 270933 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1782. Min Act: -0.0002

Data Index: 1240142 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1791. Min Act: -0.0002

Data Index: 153139 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1653. Min Act: -0.0002

Data Index: 18486 (C4 (Web Text))

Max Activating Token Index: 370