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

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

Neuron 732 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: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0005

Data Index: 398755 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0790. Min Act: -0.0005

Data Index: 807710 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0637. Min Act: -0.0005

Data Index: 1194457 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0667. Min Act: -0.0005

Data Index: 713545 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0617. Min Act: -0.0005

Data Index: 366791 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0631. Min Act: -0.0005

Data Index: 760861 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0645. Min Act: -0.0005

Data Index: 1269431 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0628. Min Act: -0.0005

Data Index: 592620 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0649. Min Act: -0.0005

Data Index: 543983 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0586. Min Act: -0.0005

Data Index: 1313140 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0615. Min Act: -0.0005

Data Index: 802133 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0624. Min Act: -0.0005

Data Index: 88183 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0623. Min Act: -0.0005

Data Index: 273826 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0608. Min Act: -0.0005

Data Index: 360252 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0594. Min Act: -0.0005

Data Index: 1112118 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0612. Min Act: -0.0005

Data Index: 473273 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0580. Min Act: -0.0005

Data Index: 449359 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0577. Min Act: -0.0005

Data Index: 381925 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0569. Min Act: -0.0005

Data Index: 727995 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0543. Min Act: -0.0005

Data Index: 789989 (C4 (Web Text))

Max Activating Token Index: 448