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

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

Neuron 51 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: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1280586 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0893. Min Act: -0.0003

Data Index: 60195 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0795. Min Act: -0.0003

Data Index: 362356 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0812. Min Act: -0.0003

Data Index: 440517 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0868. Min Act: -0.0003

Data Index: 337503 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0820. Min Act: -0.0003

Data Index: 206557 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0823. Min Act: -0.0003

Data Index: 158955 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0843. Min Act: -0.0003

Data Index: 297063 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0769. Min Act: -0.0003

Data Index: 273370 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0773. Min Act: -0.0003

Data Index: 685970 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1331948 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0859. Min Act: -0.0003

Data Index: 387455 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0799. Min Act: -0.0003

Data Index: 800863 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0791. Min Act: -0.0003

Data Index: 763877 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0830. Min Act: -0.0003

Data Index: 332587 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0822. Min Act: -0.0003

Data Index: 74377 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0724. Min Act: -0.0003

Data Index: 386017 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0782. Min Act: -0.0003

Data Index: 1253505 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0781. Min Act: -0.0003

Data Index: 1243540 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0780. Min Act: -0.0003

Data Index: 1167788 (C4 (Web Text))

Max Activating Token Index: 73