Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2183 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0893. Min Act: -0.0001

Data Index: 171523 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0867. Min Act: -0.0001

Data Index: 115802 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1235533 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0862. Min Act: -0.0001

Data Index: 859063 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0832. Min Act: -0.0001

Data Index: 378935 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0746. Min Act: -0.0001

Data Index: 964238 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0877. Min Act: -0.0001

Data Index: 575322 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0785. Min Act: -0.0001

Data Index: 826150 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0763. Min Act: -0.0001

Data Index: 62091 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0741. Min Act: -0.0001

Data Index: 53302 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0790. Min Act: -0.0001

Data Index: 904055 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0724. Min Act: -0.0001

Data Index: 528200 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0701. Min Act: -0.0001

Data Index: 550893 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1236091 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0717. Min Act: -0.0001

Data Index: 805053 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0672. Min Act: -0.0001

Data Index: 274393 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0692. Min Act: -0.0001

Data Index: 759782 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0716. Min Act: -0.0001

Data Index: 751837 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0688. Min Act: -0.0001

Data Index: 915981 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0711. Min Act: -0.0001

Data Index: 134560 (C4 (Web Text))

Max Activating Token Index: 88