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

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

Neuron 4689 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.9882. Min Act: -0.0002

Data Index: 910175 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.9426. Min Act: -0.0002

Data Index: 214602 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8189. Min Act: -0.0002

Data Index: 694940 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.9318. Min Act: -0.0002

Data Index: 1137294 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.9489. Min Act: -0.0002

Data Index: 168855 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8753. Min Act: -0.0002

Data Index: 447943 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.9459. Min Act: -0.0002

Data Index: 294172 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8896. Min Act: -0.0002

Data Index: 926839 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.9689. Min Act: -0.0002

Data Index: 331232 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8797. Min Act: -0.0002

Data Index: 1006127 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8944. Min Act: -0.0002

Data Index: 1226229 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8126. Min Act: -0.0002

Data Index: 948805 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8442. Min Act: -0.0002

Data Index: 255532 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.9623. Min Act: -0.0002

Data Index: 441545 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.0087. Min Range: -1.0087

Max Act: 1.0087. Min Act: -0.0002

Data Index: 1232355 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8014. Min Act: -0.0002

Data Index: 684341 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8841. Min Act: -0.0002

Data Index: 1246472 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8886. Min Act: -0.0002

Data Index: 320618 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7749. Min Act: -0.0002

Data Index: 508536 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.9851. Min Act: -0.0002

Data Index: 1246433 (C4 (Web Text))

Max Activating Token Index: 147