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

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

Neuron 2532 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.6269. Min Act: -0.0001

Data Index: 1018641 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.3869. Min Act: -0.0002

Data Index: 1152183 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4565. Min Act: -0.0001

Data Index: 515422 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.5248. Min Act: -0.0002

Data Index: 935269 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1860. Min Act: -0.0002

Data Index: 341130 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.2866. Min Act: -0.0001

Data Index: 133449 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4109. Min Act: -0.0002

Data Index: 799255 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.2849. Min Act: -0.0002

Data Index: 535098 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.3651. Min Act: -0.0001

Data Index: 191946 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1983. Min Act: -0.0002

Data Index: 1038577 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.3015. Min Act: -0.0002

Data Index: 659798 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.2764. Min Act: -0.0001

Data Index: 1109183 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.2616. Min Act: -0.0001

Data Index: 32501 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.2186. Min Act: -0.0002

Data Index: 234855 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1792. Min Act: -0.0002

Data Index: 788141 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1487. Min Act: -0.0002

Data Index: 843731 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1931. Min Act: -0.0001

Data Index: 831080 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1645. Min Act: -0.0001

Data Index: 31911 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1859. Min Act: -0.0002

Data Index: 1199966 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.2144. Min Act: -0.0001

Data Index: 1277376 (C4 (Web Text))

Max Activating Token Index: 370