Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1213656 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0876. Min Act: -0.0001

Data Index: 209077 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0861. Min Act: -0.0001

Data Index: 283525 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0881. Min Act: -0.0001

Data Index: 320909 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0829. Min Act: -0.0001

Data Index: 79072 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0792. Min Act: -0.0001

Data Index: 599237 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1583979 (Python Code)

Max Activating Token Index: 499

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0785. Min Act: -0.0001

Data Index: 777970 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0795. Min Act: -0.0001

Data Index: 553957 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1583176 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0711. Min Act: -0.0001

Data Index: 176717 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0716. Min Act: -0.0001

Data Index: 656401 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0754. Min Act: -0.0001

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1532500 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1601752 (Python Code)

Max Activating Token Index: 762

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1429357 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1072625 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1595178 (Python Code)

Max Activating Token Index: 945

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0675. Min Act: -0.0001

Data Index: 591774 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1480805 (Python Code)

Max Activating Token Index: 683