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

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

Neuron 248 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: 0.0943. Min Range: -0.0943

Max Act: 0.0943. Min Act: -0.0005

Data Index: 1110113 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0898. Min Act: -0.0005

Data Index: 632293 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0892. Min Act: -0.0005

Data Index: 244080 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0857. Min Act: -0.0005

Data Index: 1131373 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0868. Min Act: -0.0005

Data Index: 715412 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0865. Min Act: -0.0005

Data Index: 881611 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0870. Min Act: -0.0005

Data Index: 1199954 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0785. Min Act: -0.0005

Data Index: 1000428 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0807. Min Act: -0.0005

Data Index: 230959 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0794. Min Act: -0.0005

Data Index: 88756 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0836. Min Act: -0.0005

Data Index: 1249549 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0760. Min Act: -0.0005

Data Index: 153447 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0765. Min Act: -0.0005

Data Index: 1147176 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0746. Min Act: -0.0005

Data Index: 805009 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0745. Min Act: -0.0005

Data Index: 190477 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0722. Min Act: -0.0005

Data Index: 139560 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0736. Min Act: -0.0005

Data Index: 420093 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0723. Min Act: -0.0005

Data Index: 864341 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0739. Min Act: -0.0005

Data Index: 34383 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0692. Min Act: -0.0005

Data Index: 1667 (C4 (Web Text))

Max Activating Token Index: 694