Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1468 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1207. Min Act: -0.0003

Data Index: 522111 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0915. Min Act: -0.0003

Data Index: 363536 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0906. Min Act: -0.0003

Data Index: 1038620 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0856. Min Act: -0.0003

Data Index: 1258468 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1111907 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0835. Min Act: -0.0003

Data Index: 338923 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1294730 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1281704 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0771. Min Act: -0.0003

Data Index: 351947 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0779. Min Act: -0.0002

Data Index: 244668 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0778. Min Act: -0.0003

Data Index: 1110906 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0781. Min Act: -0.0003

Data Index: 488642 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0764. Min Act: -0.0002

Data Index: 794173 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0738. Min Act: -0.0003

Data Index: 895874 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1134268 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0721. Min Act: -0.0002

Data Index: 30455 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0733. Min Act: -0.0003

Data Index: 169961 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0718. Min Act: -0.0003

Data Index: 783103 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0712. Min Act: -0.0003

Data Index: 591670 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1513636 (Python Code)

Max Activating Token Index: 898