Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3452 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2898. Min Range: -4.2898

Max Act: 4.2898. Min Act: -0.0000

Data Index: 33153 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.8757. Min Act: -0.0000

Data Index: 1091203 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.8429. Min Act: -0.0000

Data Index: 739401 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.9327. Min Act: -0.0000

Data Index: 447432 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.8603. Min Act: -0.0000

Data Index: 1214079 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.5571. Min Act: -0.0000

Data Index: 813953 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.5030. Min Act: -0.0000

Data Index: 546723 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.4651. Min Act: -0.0000

Data Index: 809163 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.6706. Min Act: -0.0000

Data Index: 444409 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.4698. Min Act: -0.0000

Data Index: 642382 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.1077. Min Act: -0.0000

Data Index: 254103 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 4.2898. Min Range: -4.2898

Max Act: 2.9229. Min Act: -0.0000

Data Index: 691363 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.0333. Min Act: -0.0000

Data Index: 265094 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 4.2898. Min Range: -4.2898

Max Act: 2.9743. Min Act: -0.0000

Data Index: 103974 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 4.2898. Min Range: -4.2898

Max Act: 3.0825. Min Act: -0.0000

Data Index: 434488 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 4.2898. Min Range: -4.2898

Max Act: 2.9177. Min Act: -0.0000

Data Index: 984981 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 4.2898. Min Range: -4.2898

Max Act: 2.9685. Min Act: -0.0000

Data Index: 232038 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 4.2898. Min Range: -4.2898

Max Act: 2.8168. Min Act: -0.0000

Data Index: 270288 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 4.2898. Min Range: -4.2898

Max Act: 2.7970. Min Act: -0.0000

Data Index: 1356874 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 4.2898. Min Range: -4.2898

Max Act: 2.8282. Min Act: -0.0000

Data Index: 862997 (C4 (Web Text))

Max Activating Token Index: 570