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

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

Neuron 1484 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1196. Min Act: -0.0005

Data Index: 1091623 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1129. Min Act: -0.0005

Data Index: 298889 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1115. Min Act: -0.0005

Data Index: 1162238 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1046. Min Act: -0.0005

Data Index: 961587 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1000. Min Act: -0.0005

Data Index: 469264 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1023. Min Act: -0.0005

Data Index: 1234787 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1048. Min Act: -0.0005

Data Index: 1220213 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1078. Min Act: -0.0005

Data Index: 1174689 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0958. Min Act: -0.0005

Data Index: 258189 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1008. Min Act: -0.0005

Data Index: 401920 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0896. Min Act: -0.0005

Data Index: 79081 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0866. Min Act: -0.0005

Data Index: 617705 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0967. Min Act: -0.0005

Data Index: 136665 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0937. Min Act: -0.0005

Data Index: 1119717 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0919. Min Act: -0.0005

Data Index: 758762 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0910. Min Act: -0.0005

Data Index: 132188 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0832. Min Act: -0.0005

Data Index: 1177296 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0885. Min Act: -0.0005

Data Index: 1052150 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0876. Min Act: -0.0005

Data Index: 444457 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0901. Min Act: -0.0005

Data Index: 672452 (C4 (Web Text))

Max Activating Token Index: 280