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

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

Neuron 482 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0003

Data Index: 163631 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0751. Min Act: -0.0003

Data Index: 419680 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0713. Min Act: -0.0003

Data Index: 857669 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0680. Min Act: -0.0003

Data Index: 104904 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1834 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0715. Min Act: -0.0003

Data Index: 934912 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0685. Min Act: -0.0003

Data Index: 320564 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0625. Min Act: -0.0003

Data Index: 426753 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0629. Min Act: -0.0003

Data Index: 248708 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1343292 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0590. Min Act: -0.0003

Data Index: 911108 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0599. Min Act: -0.0003

Data Index: 17138 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0587. Min Act: -0.0003

Data Index: 304993 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1135163 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0646. Min Act: -0.0003

Data Index: 217247 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0538. Min Act: -0.0003

Data Index: 834999 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1329888 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0609. Min Act: -0.0003

Data Index: 862778 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0571. Min Act: -0.0003

Data Index: 726439 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0549. Min Act: -0.0003

Data Index: 14784 (C4 (Web Text))

Max Activating Token Index: 236