Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 380 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0796. Min Act: -0.0003

Data Index: 594051 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0003

Data Index: 696233 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0773. Min Act: -0.0003

Data Index: 556662 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0791. Min Act: -0.0003

Data Index: 701559 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0810. Min Act: -0.0003

Data Index: 943738 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0769. Min Act: -0.0003

Data Index: 727340 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0787. Min Act: -0.0003

Data Index: 1013075 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0736. Min Act: -0.0003

Data Index: 439161 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0778. Min Act: -0.0003

Data Index: 502351 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0757. Min Act: -0.0003

Data Index: 650583 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0735. Min Act: -0.0003

Data Index: 614303 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0725. Min Act: -0.0003

Data Index: 565138 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0738. Min Act: -0.0003

Data Index: 701257 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0729. Min Act: -0.0003

Data Index: 326191 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0748. Min Act: -0.0003

Data Index: 55812 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1352417 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0713. Min Act: -0.0004

Data Index: 1027916 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0693. Min Act: -0.0003

Data Index: 489650 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0694. Min Act: -0.0003

Data Index: 342754 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0741. Min Act: -0.0003

Data Index: 621632 (C4 (Web Text))

Max Activating Token Index: 609