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

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

Neuron 3784 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: 0.0847. Min Range: -0.0847

Max Act: 0.0847. Min Act: -0.0003

Data Index: 394807 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0758. Min Act: -0.0003

Data Index: 96034 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0765. Min Act: -0.0003

Data Index: 809020 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1297093 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0743. Min Act: -0.0002

Data Index: 345675 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0702. Min Act: -0.0003

Data Index: 495459 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0703. Min Act: -0.0002

Data Index: 625970 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0705. Min Act: -0.0003

Data Index: 97840 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0685. Min Act: -0.0002

Data Index: 620688 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0644. Min Act: -0.0003

Data Index: 655065 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0632. Min Act: -0.0003

Data Index: 923879 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1455346 (Python Code)

Max Activating Token Index: 873

Text #12

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0678. Min Act: -0.0003

Data Index: 904796 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0601. Min Act: -0.0003

Data Index: 227603 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1136086 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1504976 (Python Code)

Max Activating Token Index: 543

Text #16

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0619. Min Act: -0.0003

Data Index: 618851 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0623. Min Act: -0.0003

Data Index: 673527 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0612. Min Act: -0.0003

Data Index: 326438 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1093531 (C4 (Web Text))

Max Activating Token Index: 901