Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5837 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1037680 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0904. Min Act: -0.0002

Data Index: 280691 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1332546 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0872. Min Act: -0.0002

Data Index: 409619 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0838. Min Act: -0.0002

Data Index: 546130 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0860. Min Act: -0.0002

Data Index: 123979 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1079947 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0830. Min Act: -0.0002

Data Index: 587741 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1103096 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0837. Min Act: -0.0002

Data Index: 902629 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0804. Min Act: -0.0002

Data Index: 58550 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1008634 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0792. Min Act: -0.0002

Data Index: 268759 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0773. Min Act: -0.0002

Data Index: 269557 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0758. Min Act: -0.0002

Data Index: 40407 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1199154 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0743. Min Act: -0.0002

Data Index: 948604 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0770. Min Act: -0.0002

Data Index: 330116 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0743. Min Act: -0.0002

Data Index: 534401 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0757. Min Act: -0.0002

Data Index: 240293 (C4 (Web Text))

Max Activating Token Index: 895