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

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

Neuron 4688 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1237. Min Act: -0.0001

Data Index: 239796 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1125. Min Act: -0.0001

Data Index: 960467 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1172753 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0911. Min Act: -0.0001

Data Index: 659154 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0995. Min Act: -0.0001

Data Index: 976477 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0939. Min Act: -0.0001

Data Index: 702724 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0907. Min Act: -0.0001

Data Index: 402171 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0952. Min Act: -0.0001

Data Index: 283452 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0912. Min Act: -0.0001

Data Index: 569282 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0877. Min Act: -0.0001

Data Index: 610688 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0850. Min Act: -0.0001

Data Index: 81517 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0905. Min Act: -0.0001

Data Index: 507971 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1133552 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0875. Min Act: -0.0001

Data Index: 899697 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0884. Min Act: -0.0001

Data Index: 647438 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0901. Min Act: -0.0001

Data Index: 248188 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0890. Min Act: -0.0001

Data Index: 549821 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0923. Min Act: -0.0001

Data Index: 522503 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0740. Min Act: -0.0001

Data Index: 166852 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0901. Min Act: -0.0001

Data Index: 180383 (C4 (Web Text))

Max Activating Token Index: 5