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

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

Neuron 173 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0003

Data Index: 484118 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0905. Min Act: -0.0003

Data Index: 362746 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0872. Min Act: -0.0003

Data Index: 1115217 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1164533 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0847. Min Act: -0.0003

Data Index: 356015 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0845. Min Act: -0.0003

Data Index: 851928 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0844. Min Act: -0.0003

Data Index: 326059 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0836. Min Act: -0.0003

Data Index: 555195 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0831. Min Act: -0.0003

Data Index: 784643 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0798. Min Act: -0.0003

Data Index: 270763 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0801. Min Act: -0.0003

Data Index: 1291852 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0803. Min Act: -0.0003

Data Index: 30496 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0830. Min Act: -0.0002

Data Index: 310664 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0825. Min Act: -0.0003

Data Index: 64537 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1030435 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1181677 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0818. Min Act: -0.0003

Data Index: 347140 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0814. Min Act: -0.0003

Data Index: 78821 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0826. Min Act: -0.0002

Data Index: 400074 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0793. Min Act: -0.0002

Data Index: 115468 (C4 (Web Text))

Max Activating Token Index: 480