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

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

Neuron 2892 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0901. Min Act: -0.0003

Data Index: 561305 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0889. Min Act: -0.0003

Data Index: 269245 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0851. Min Act: -0.0003

Data Index: 49939 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0847. Min Act: -0.0003

Data Index: 1110751 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1031462 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0830. Min Act: -0.0002

Data Index: 289432 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0799. Min Act: -0.0003

Data Index: 466263 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0768. Min Act: -0.0003

Data Index: 430484 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0752. Min Act: -0.0003

Data Index: 538587 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0807. Min Act: -0.0003

Data Index: 1179228 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0755. Min Act: -0.0003

Data Index: 914013 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0733. Min Act: -0.0003

Data Index: 645082 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0781. Min Act: -0.0003

Data Index: 885228 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0591. Min Act: -0.0003

Data Index: 416035 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0666. Min Act: -0.0002

Data Index: 327295 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0739. Min Act: -0.0003

Data Index: 459339 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0728. Min Act: -0.0003

Data Index: 120467 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0691. Min Act: -0.0003

Data Index: 878450 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0710. Min Act: -0.0003

Data Index: 28217 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0713. Min Act: -0.0002

Data Index: 943919 (C4 (Web Text))

Max Activating Token Index: 167