Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1981 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0005

Data Index: 21024 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0792. Min Act: -0.0005

Data Index: 725850 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0777. Min Act: -0.0005

Data Index: 524195 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0788. Min Act: -0.0005

Data Index: 746949 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0754. Min Act: -0.0005

Data Index: 431665 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0776. Min Act: -0.0005

Data Index: 885229 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0744. Min Act: -0.0005

Data Index: 757389 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0755. Min Act: -0.0005

Data Index: 469072 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0754. Min Act: -0.0005

Data Index: 1238972 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0751. Min Act: -0.0005

Data Index: 661147 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0747. Min Act: -0.0005

Data Index: 207946 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0763. Min Act: -0.0005

Data Index: 712706 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0732. Min Act: -0.0005

Data Index: 628408 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0743. Min Act: -0.0005

Data Index: 521813 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0739. Min Act: -0.0005

Data Index: 569560 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0711. Min Act: -0.0005

Data Index: 951942 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0723. Min Act: -0.0005

Data Index: 1288841 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0734. Min Act: -0.0005

Data Index: 887688 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0729. Min Act: -0.0005

Data Index: 572198 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0743. Min Act: -0.0005

Data Index: 556792 (C4 (Web Text))

Max Activating Token Index: 85