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

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

Neuron 5049 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: 1.6810. Min Range: -1.6810

Max Act: 1.6737. Min Act: -0.0001

Data Index: 1262049 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.6810. Min Act: -0.0000

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.5958. Min Act: -0.0001

Data Index: 1357825 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4719. Min Act: -0.0001

Data Index: 498223 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.6678. Min Act: -0.0001

Data Index: 1035538 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4828. Min Act: -0.0001

Data Index: 943392 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4640. Min Act: -0.0001

Data Index: 439624 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4945. Min Act: -0.0000

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4945. Min Act: -0.0001

Data Index: 180131 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4723. Min Act: -0.0001

Data Index: 885256 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4694. Min Act: -0.0000

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4933. Min Act: -0.0001

Data Index: 922600 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4607. Min Act: -0.0001

Data Index: 93610 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.3644. Min Act: -0.0001

Data Index: 474447 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.3973. Min Act: -0.0001

Data Index: 677002 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4656. Min Act: -0.0001

Data Index: 229606 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4120. Min Act: -0.0001

Data Index: 1170098 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.3380. Min Act: -0.0001

Data Index: 694870 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4107. Min Act: -0.0001

Data Index: 800469 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4693. Min Act: -0.0001

Data Index: 1328345 (C4 (Web Text))

Max Activating Token Index: 803