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

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

Neuron 513 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1524. Min Act: -0.0003

Data Index: 1257926 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1512. Min Act: -0.0003

Data Index: 591349 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1372. Min Act: -0.0003

Data Index: 330388 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1303. Min Act: -0.0003

Data Index: 39146 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1256. Min Act: -0.0003

Data Index: 859113 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1117. Min Act: -0.0003

Data Index: 153588 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1046. Min Act: -0.0003

Data Index: 1167760 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1070390 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0828. Min Act: -0.0003

Data Index: 117326 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0809. Min Act: -0.0003

Data Index: 613660 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0819. Min Act: -0.0003

Data Index: 553682 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1241623 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0806. Min Act: -0.0003

Data Index: 52151 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0805. Min Act: -0.0003

Data Index: 863630 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0810. Min Act: -0.0003

Data Index: 1290739 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0740. Min Act: -0.0003

Data Index: 669330 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0793. Min Act: -0.0003

Data Index: 853313 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0740. Min Act: -0.0003

Data Index: 666410 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0753. Min Act: -0.0003

Data Index: 298124 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0763. Min Act: -0.0003

Data Index: 482954 (C4 (Web Text))

Max Activating Token Index: 938