Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 961 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0001

Data Index: 115934 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0990. Min Act: -0.0001

Data Index: 911397 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1023. Min Act: -0.0001

Data Index: 726764 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0934. Min Act: -0.0001

Data Index: 382762 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0806. Min Act: -0.0001

Data Index: 318819 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0801. Min Act: -0.0001

Data Index: 500372 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1119161 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0758. Min Act: -0.0001

Data Index: 422005 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1102862 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0796. Min Act: -0.0001

Data Index: 155459 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0747. Min Act: -0.0001

Data Index: 551856 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1051783 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0733. Min Act: -0.0001

Data Index: 50327 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0711. Min Act: -0.0001

Data Index: 139169 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1190060 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0743. Min Act: -0.0001

Data Index: 309023 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0710. Min Act: -0.0001

Data Index: 846731 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0734. Min Act: -0.0001

Data Index: 884440 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0676. Min Act: -0.0001

Data Index: 121577 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1061880 (C4 (Web Text))

Max Activating Token Index: 842