Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 981 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.5368. Min Act: -0.0001

Data Index: 488179 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.2622. Min Act: -0.0001

Data Index: 769906 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.2852. Min Act: -0.0001

Data Index: 809089 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1105997 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1493577 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0957. Min Act: -0.0001

Data Index: 380119 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0909. Min Act: -0.0001

Data Index: 39650 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0869. Min Act: -0.0001

Data Index: 977212 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1164763 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0788. Min Act: -0.0001

Data Index: 200704 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1156093 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0702. Min Act: -0.0001

Data Index: 733382 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0730. Min Act: -0.0001

Data Index: 777246 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0721. Min Act: -0.0001

Data Index: 397603 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0716. Min Act: -0.0001

Data Index: 28778 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0796. Min Act: -0.0001

Data Index: 744529 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0678. Min Act: -0.0001

Data Index: 355521 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0699. Min Act: -0.0001

Data Index: 206177 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0635. Min Act: -0.0001

Data Index: 784334 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.0666. Min Act: -0.0001

Data Index: 142979 (C4 (Web Text))

Max Activating Token Index: 10