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

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

Neuron 2161 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: 0.1094. Min Range: -0.1094

Max Act: 0.1094. Min Act: -0.0002

Data Index: 573690 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.1024. Min Act: -0.0002

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0917. Min Act: -0.0002

Data Index: 961360 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0977. Min Act: -0.0002

Data Index: 304891 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0962. Min Act: -0.0002

Data Index: 67101 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0899. Min Act: -0.0002

Data Index: 664514 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1053837 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0899. Min Act: -0.0002

Data Index: 215300 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0914. Min Act: -0.0002

Data Index: 876407 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0851. Min Act: -0.0002

Data Index: 617251 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0886. Min Act: -0.0002

Data Index: 437661 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0972. Min Act: -0.0002

Data Index: 485427 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1654516 (Python Code)

Max Activating Token Index: 514

Text #13

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0825. Min Act: -0.0002

Data Index: 281434 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1134130 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0930. Min Act: -0.0002

Data Index: 918195 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0909. Min Act: -0.0002

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0910. Min Act: -0.0002

Data Index: 237932 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1096461 (C4 (Web Text))

Max Activating Token Index: 84