Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3687 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1177. Min Act: -0.0002

Data Index: 1283195 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1214. Min Act: -0.0002

Data Index: 544608 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0964. Min Act: -0.0002

Data Index: 77903 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1007. Min Act: -0.0002

Data Index: 939413 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1014. Min Act: -0.0002

Data Index: 843993 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1276088 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0957. Min Act: -0.0002

Data Index: 566660 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0993. Min Act: -0.0002

Data Index: 145086 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0878. Min Act: -0.0002

Data Index: 35628 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0951. Min Act: -0.0002

Data Index: 237284 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1250304 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1029527 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0891. Min Act: -0.0002

Data Index: 104457 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0831. Min Act: -0.0002

Data Index: 890514 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1577528 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0859. Min Act: -0.0002

Data Index: 523996 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0901. Min Act: -0.0002

Data Index: 28663 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0905. Min Act: -0.0002

Data Index: 607500 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0858. Min Act: -0.0003

Data Index: 393302 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0862. Min Act: -0.0002

Data Index: 710689 (C4 (Web Text))

Max Activating Token Index: 213