Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1991 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1301792 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1224820 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0848. Min Act: -0.0002

Data Index: 24173 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0834. Min Act: -0.0002

Data Index: 580845 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0790. Min Act: -0.0002

Data Index: 39519 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0795. Min Act: -0.0002

Data Index: 4316 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0771. Min Act: -0.0002

Data Index: 617246 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0798. Min Act: -0.0002

Data Index: 502758 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1295695 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0732. Min Act: -0.0002

Data Index: 620262 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0708. Min Act: -0.0002

Data Index: 409586 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0676. Min Act: -0.0002

Data Index: 640382 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0735. Min Act: -0.0002

Data Index: 186753 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0679. Min Act: -0.0002

Data Index: 230681 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1315878 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0684. Min Act: -0.0002

Data Index: 106793 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0662. Min Act: -0.0002

Data Index: 50231 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0671. Min Act: -0.0002

Data Index: 466380 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0693. Min Act: -0.0002

Data Index: 191663 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1089907 (C4 (Web Text))

Max Activating Token Index: 380