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

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

Neuron 2744 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3699. Min Act: -0.0001

Data Index: 475740 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3379. Min Act: -0.0001

Data Index: 1037153 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2981. Min Act: -0.0001

Data Index: 528492 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2934. Min Act: -0.0001

Data Index: 240960 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2653. Min Act: -0.0001

Data Index: 234773 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2619. Min Act: -0.0001

Data Index: 225307 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2667. Min Act: -0.0001

Data Index: 1138130 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2662. Min Act: -0.0001

Data Index: 470767 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2741. Min Act: -0.0001

Data Index: 90543 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2781. Min Act: -0.0001

Data Index: 1018122 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2748. Min Act: -0.0001

Data Index: 91437 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2544. Min Act: -0.0001

Data Index: 325013 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2507. Min Act: -0.0000

Data Index: 136666 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2621. Min Act: -0.0001

Data Index: 255231 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1137718 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2494. Min Act: -0.0001

Data Index: 553264 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2632. Min Act: -0.0001

Data Index: 1252863 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1087678 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2275. Min Act: -0.0001

Data Index: 220007 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2652. Min Act: -0.0001

Data Index: 780846 (C4 (Web Text))

Max Activating Token Index: 146