Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4494 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1153. Min Act: -0.0000

Data Index: 499016 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1012. Min Act: -0.0000

Data Index: 820555 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0931. Min Act: -0.0000

Data Index: 854024 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0906. Min Act: -0.0000

Data Index: 805408 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0888. Min Act: -0.0000

Data Index: 803788 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0886. Min Act: -0.0000

Data Index: 215484 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0846. Min Act: -0.0000

Data Index: 451664 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0907. Min Act: -0.0000

Data Index: 512862 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0857. Min Act: -0.0000

Data Index: 271750 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0852. Min Act: -0.0000

Data Index: 310713 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0809. Min Act: -0.0000

Data Index: 395393 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1071909 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0780. Min Act: -0.0000

Data Index: 400813 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0767. Min Act: -0.0000

Data Index: 469811 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0795. Min Act: -0.0000

Data Index: 945317 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0799. Min Act: -0.0000

Data Index: 866838 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0795. Min Act: -0.0000

Data Index: 990982 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0761. Min Act: -0.0000

Data Index: 798197 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0760. Min Act: -0.0000

Data Index: 576853 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0774. Min Act: -0.0000

Data Index: 1317570 (C4 (Web Text))

Max Activating Token Index: 768