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

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

Neuron 571 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: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0002

Data Index: 696633 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0443. Min Act: -0.0002

Data Index: 882983 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0421. Min Act: -0.0002

Data Index: 562618 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1242069 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0395. Min Act: -0.0002

Data Index: 484676 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1019732 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0401. Min Act: -0.0002

Data Index: 76695 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1189058 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0391. Min Act: -0.0002

Data Index: 637538 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1055205 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0382. Min Act: -0.0002

Data Index: 320406 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0389. Min Act: -0.0002

Data Index: 108190 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0384. Min Act: -0.0002

Data Index: 916116 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0379. Min Act: -0.0002

Data Index: 215243 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0382. Min Act: -0.0002

Data Index: 872107 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0362. Min Act: -0.0002

Data Index: 576547 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0373. Min Act: -0.0002

Data Index: 559264 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0372. Min Act: -0.0002

Data Index: 509727 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0367. Min Act: -0.0002

Data Index: 557501 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0372. Min Act: -0.0002

Data Index: 661891 (C4 (Web Text))

Max Activating Token Index: 351