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

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

Neuron 2830 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1014511 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1018723 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0872. Min Act: -0.0002

Data Index: 649042 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0793. Min Act: -0.0002

Data Index: 886411 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0794. Min Act: -0.0001

Data Index: 639366 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0781. Min Act: -0.0002

Data Index: 13264 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0772. Min Act: -0.0002

Data Index: 876731 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1311951 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0752. Min Act: -0.0002

Data Index: 809110 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0751. Min Act: -0.0001

Data Index: 531570 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1337405 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0741. Min Act: -0.0002

Data Index: 173661 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0719. Min Act: -0.0002

Data Index: 669868 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0745. Min Act: -0.0002

Data Index: 798743 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0717. Min Act: -0.0002

Data Index: 874762 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1120737 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0707. Min Act: -0.0002

Data Index: 744212 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0679. Min Act: -0.0002

Data Index: 106340 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1164803 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0702. Min Act: -0.0002

Data Index: 804428 (C4 (Web Text))

Max Activating Token Index: 278