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

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

Neuron 2826 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6648. Min Act: -0.0001

Data Index: 874382 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4864. Min Act: -0.0001

Data Index: 666737 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4814. Min Act: -0.0001

Data Index: 989167 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4698. Min Act: -0.0001

Data Index: 108289 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4601. Min Act: -0.0001

Data Index: 1203723 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4780. Min Act: -0.0001

Data Index: 1213372 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4806. Min Act: -0.0001

Data Index: 126768 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4827. Min Act: -0.0001

Data Index: 392944 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4142. Min Act: -0.0001

Data Index: 1176112 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4728. Min Act: -0.0001

Data Index: 1197297 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4775. Min Act: -0.0001

Data Index: 1217463 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4419. Min Act: -0.0001

Data Index: 760464 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4468. Min Act: -0.0001

Data Index: 1121640 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4969. Min Act: -0.0001

Data Index: 1103631 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1256649 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4765. Min Act: -0.0001

Data Index: 228514 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5071. Min Act: -0.0001

Data Index: 1187119 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4705. Min Act: -0.0001

Data Index: 976902 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4399. Min Act: -0.0001

Data Index: 813890 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4414. Min Act: -0.0001

Data Index: 1289679 (C4 (Web Text))

Max Activating Token Index: 877