Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 538 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1049. Min Act: -0.0003

Data Index: 594506 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0897. Min Act: -0.0003

Data Index: 540711 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0889. Min Act: -0.0003

Data Index: 95662 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0860. Min Act: -0.0003

Data Index: 963662 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0825. Min Act: -0.0003

Data Index: 1300176 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0839. Min Act: -0.0003

Data Index: 571874 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0803. Min Act: -0.0003

Data Index: 849033 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0810. Min Act: -0.0003

Data Index: 89347 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0806. Min Act: -0.0003

Data Index: 671016 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0789. Min Act: -0.0003

Data Index: 529109 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0798. Min Act: -0.0003

Data Index: 1243156 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0766. Min Act: -0.0003

Data Index: 153319 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0774. Min Act: -0.0003

Data Index: 488515 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0764. Min Act: -0.0003

Data Index: 105313 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0774. Min Act: -0.0003

Data Index: 321822 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1356359 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0745. Min Act: -0.0004

Data Index: 897815 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0725. Min Act: -0.0004

Data Index: 1184877 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1271743 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0727. Min Act: -0.0003

Data Index: 167054 (C4 (Web Text))

Max Activating Token Index: 517