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

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

Neuron 449 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.2056. Min Act: -0.0000

Data Index: 558686 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.0939. Min Act: -0.0000

Data Index: 411419 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.2109. Min Act: -0.0000

Data Index: 532731 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.0654. Min Act: -0.0000

Data Index: 279988 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.0572. Min Act: -0.0000

Data Index: 1281951 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.1419. Min Act: -0.0000

Data Index: 1018893 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.9106. Min Act: -0.0000

Data Index: 973658 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.0769. Min Act: -0.0000

Data Index: 549188 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.0059. Min Act: -0.0000

Data Index: 878678 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.0159. Min Act: -0.0000

Data Index: 158985 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.9959. Min Act: -0.0000

Data Index: 1250928 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 2.2109. Min Range: -2.2109

Max Act: 2.0940. Min Act: -0.0000

Data Index: 443806 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.8823. Min Act: -0.0000

Data Index: 1337389 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.8153. Min Act: -0.0000

Data Index: 1059720 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.9219. Min Act: -0.0000

Data Index: 797134 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.6129. Min Act: -0.0000

Data Index: 130391 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.8227. Min Act: -0.0000

Data Index: 879109 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.8173. Min Act: -0.0000

Data Index: 353883 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.8148. Min Act: -0.0000

Data Index: 1342695 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 2.2109. Min Range: -2.2109

Max Act: 1.6384. Min Act: -0.0000

Data Index: 303601 (C4 (Web Text))

Max Activating Token Index: 612