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

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

Neuron 4199 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.5146. Min Act: -0.0001

Data Index: 1125274 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.5903. Min Act: -0.0001

Data Index: 987869 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.5129. Min Act: -0.0001

Data Index: 824155 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.1498. Min Act: -0.0001

Data Index: 1074730 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.1166. Min Act: -0.0001

Data Index: 949242 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.1892. Min Act: -0.0001

Data Index: 683094 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.1007. Min Act: -0.0001

Data Index: 832038 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.1105. Min Act: -0.0001

Data Index: 179172 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.0312. Min Act: -0.0001

Data Index: 1070688 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.1420. Min Act: -0.0001

Data Index: 242822 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 1.5903. Min Range: -1.5903

Max Act: 1.0575. Min Act: -0.0001

Data Index: 1323424 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 1.5903. Min Range: -1.5903

Max Act: 0.9868. Min Act: -0.0001

Data Index: 845634 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 1.5903. Min Range: -1.5903

Max Act: 0.9743. Min Act: -0.0001

Data Index: 83735 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 1.5903. Min Range: -1.5903

Max Act: 0.9816. Min Act: -0.0001

Data Index: 885256 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 1.5903. Min Range: -1.5903

Max Act: 0.9363. Min Act: -0.0001

Data Index: 1232493 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 1.5903. Min Range: -1.5903

Max Act: 0.8778. Min Act: -0.0001

Data Index: 136166 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 1.5903. Min Range: -1.5903

Max Act: 0.8834. Min Act: -0.0001

Data Index: 219095 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 1.5903. Min Range: -1.5903

Max Act: 0.8461. Min Act: -0.0001

Data Index: 123324 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.5903. Min Range: -1.5903

Max Act: 0.7134. Min Act: -0.0001

Data Index: 288482 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 1.5903. Min Range: -1.5903

Max Act: 0.7841. Min Act: -0.0001

Data Index: 500843 (C4 (Web Text))

Max Activating Token Index: 622