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

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

Neuron 673 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: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0001

Data Index: 417587 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1356023 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1198378 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0870. Min Act: -0.0001

Data Index: 495741 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0726. Min Act: -0.0001

Data Index: 749703 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0762. Min Act: -0.0001

Data Index: 416233 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0736. Min Act: -0.0001

Data Index: 146251 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0785. Min Act: -0.0001

Data Index: 163615 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1339816 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0744. Min Act: -0.0001

Data Index: 160512 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0698. Min Act: -0.0001

Data Index: 944154 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1108393 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0751. Min Act: -0.0001

Data Index: 987336 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0706. Min Act: -0.0001

Data Index: 432375 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0698. Min Act: -0.0001

Data Index: 792460 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0717. Min Act: -0.0001

Data Index: 198036 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0647. Min Act: -0.0001

Data Index: 323352 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0701. Min Act: -0.0001

Data Index: 319614 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0645. Min Act: -0.0001

Data Index: 238484 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1289228 (C4 (Web Text))

Max Activating Token Index: 57