Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 668 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0894. Min Act: -0.0003

Data Index: 1211189 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0702. Min Act: -0.0003

Data Index: 79256 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0639. Min Act: -0.0003

Data Index: 76258 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0616. Min Act: -0.0003

Data Index: 319243 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1275000 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0625. Min Act: -0.0003

Data Index: 339418 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0591. Min Act: -0.0003

Data Index: 641201 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0595. Min Act: -0.0003

Data Index: 929155 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0565. Min Act: -0.0004

Data Index: 372716 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0591. Min Act: -0.0003

Data Index: 476947 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0576. Min Act: -0.0004

Data Index: 767301 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0582. Min Act: -0.0003

Data Index: 282514 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0576. Min Act: -0.0003

Data Index: 316991 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0551. Min Act: -0.0003

Data Index: 256090 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0577. Min Act: -0.0003

Data Index: 753360 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1052300 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0561. Min Act: -0.0003

Data Index: 789235 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0549. Min Act: -0.0003

Data Index: 160762 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0548. Min Act: -0.0003

Data Index: 173838 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0548. Min Act: -0.0003

Data Index: 534037 (C4 (Web Text))

Max Activating Token Index: 13