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

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

Neuron 714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1298937 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0759. Min Act: -0.0002

Data Index: 122280 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0767. Min Act: -0.0002

Data Index: 417013 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0750. Min Act: -0.0002

Data Index: 757527 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0768. Min Act: -0.0002

Data Index: 846451 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1081479 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0743. Min Act: -0.0002

Data Index: 139919 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1049477 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0704. Min Act: -0.0002

Data Index: 455259 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0702. Min Act: -0.0002

Data Index: 596292 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0727. Min Act: -0.0002

Data Index: 919517 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0731. Min Act: -0.0002

Data Index: 318494 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0679. Min Act: -0.0002

Data Index: 347066 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0723. Min Act: -0.0002

Data Index: 411237 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0719. Min Act: -0.0002

Data Index: 447079 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1148323 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0742. Min Act: -0.0002

Data Index: 756379 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0675. Min Act: -0.0002

Data Index: 526393 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0671. Min Act: -0.0002

Data Index: 460686 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0685. Min Act: -0.0002

Data Index: 516284 (C4 (Web Text))

Max Activating Token Index: 776