Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6752. Min Act: -0.0000

Data Index: 791597 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6551. Min Act: -0.0001

Data Index: 596035 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6456. Min Act: -0.0001

Data Index: 523137 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6205. Min Act: -0.0000

Data Index: 119463 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5912. Min Act: -0.0001

Data Index: 346970 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6069. Min Act: -0.0001

Data Index: 115564 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1077241 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1272003 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1308074 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5944. Min Act: -0.0000

Data Index: 202365 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6102. Min Act: -0.0001

Data Index: 732872 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6100. Min Act: -0.0000

Data Index: 404794 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6088. Min Act: -0.0001

Data Index: 936359 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6044. Min Act: -0.0000

Data Index: 181920 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5807. Min Act: -0.0001

Data Index: 142882 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6005. Min Act: -0.0001

Data Index: 809690 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5911. Min Act: -0.0000

Data Index: 66760 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6085. Min Act: -0.0001

Data Index: 673329 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5648. Min Act: -0.0001

Data Index: 28948 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5651. Min Act: -0.0001

Data Index: 57020 (C4 (Web Text))

Max Activating Token Index: 126