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

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

Neuron 2675 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1622. Min Act: -0.0002

Data Index: 1394987 (Python Code)

Max Activating Token Index: 969

Text #1

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1398677 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0989. Min Act: -0.0002

Data Index: 798906 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0922. Min Act: -0.0002

Data Index: 798556 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1195799 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1210521 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1656899 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1287904 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0841. Min Act: -0.0002

Data Index: 165767 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1620679 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0737. Min Act: -0.0002

Data Index: 52337 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1528404 (Python Code)

Max Activating Token Index: 744

Text #12

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0780. Min Act: -0.0002

Data Index: 702979 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0716. Min Act: -0.0002

Data Index: 652087 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1567343 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1171003 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0795. Min Act: -0.0002

Data Index: 66650 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0786. Min Act: -0.0002

Data Index: 15751 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1401618 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0774. Min Act: -0.0002

Data Index: 726709 (C4 (Web Text))

Max Activating Token Index: 881