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

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

Neuron 711 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2645. Min Act: -0.0004

Data Index: 1055754 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2411. Min Act: -0.0004

Data Index: 510523 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2219. Min Act: -0.0004

Data Index: 1104826 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2090. Min Act: -0.0004

Data Index: 1296984 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2177. Min Act: -0.0004

Data Index: 1022788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1881. Min Act: -0.0004

Data Index: 175736 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1770. Min Act: -0.0004

Data Index: 802029 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1774. Min Act: -0.0004

Data Index: 548118 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1778. Min Act: -0.0004

Data Index: 1025050 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1687. Min Act: -0.0004

Data Index: 481944 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1622. Min Act: -0.0004

Data Index: 584592 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1611. Min Act: -0.0004

Data Index: 1166179 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1657. Min Act: -0.0004

Data Index: 1074218 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1590. Min Act: -0.0004

Data Index: 1252470 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1717. Min Act: -0.0004

Data Index: 668145 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1518. Min Act: -0.0004

Data Index: 1154607 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1564. Min Act: -0.0004

Data Index: 162783 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1492. Min Act: -0.0004

Data Index: 1157383 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1546. Min Act: -0.0004

Data Index: 962606 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1593. Min Act: -0.0004

Data Index: 1122910 (C4 (Web Text))

Max Activating Token Index: 87