Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1025 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1244583 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0889. Min Act: -0.0003

Data Index: 43017 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0822. Min Act: -0.0003

Data Index: 766855 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0843. Min Act: -0.0003

Data Index: 481560 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0796. Min Act: -0.0003

Data Index: 264444 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0771. Min Act: -0.0003

Data Index: 679293 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0802. Min Act: -0.0003

Data Index: 153943 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0709. Min Act: -0.0003

Data Index: 483468 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0756. Min Act: -0.0003

Data Index: 668427 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0756. Min Act: -0.0003

Data Index: 306007 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0713. Min Act: -0.0003

Data Index: 1149111 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0731. Min Act: -0.0003

Data Index: 666233 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0702. Min Act: -0.0003

Data Index: 116325 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1033345 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0730. Min Act: -0.0003

Data Index: 615571 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0703. Min Act: -0.0003

Data Index: 372289 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0719. Min Act: -0.0003

Data Index: 345762 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0710. Min Act: -0.0003

Data Index: 356928 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0675. Min Act: -0.0003

Data Index: 169336 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1167507 (C4 (Web Text))

Max Activating Token Index: 368