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

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

Neuron 14 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: 0.0563. Min Range: -0.0563

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1582514 (Python Code)

Max Activating Token Index: 826

Text #1

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1525425 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0486. Min Act: -0.0002

Data Index: 682239 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1492099 (Python Code)

Max Activating Token Index: 578

Text #4

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0476. Min Act: -0.0002

Data Index: 582655 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1039290 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0458. Min Act: -0.0002

Data Index: 268190 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1466801 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1120927 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1621265 (Python Code)

Max Activating Token Index: 822

Text #10

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0430. Min Act: -0.0002

Data Index: 825584 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0433. Min Act: -0.0002

Data Index: 444263 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1255590 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0425. Min Act: -0.0002

Data Index: 396988 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0428. Min Act: -0.0002

Data Index: 532822 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0420. Min Act: -0.0002

Data Index: 433526 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0421. Min Act: -0.0001

Data Index: 500341 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0425. Min Act: -0.0002

Data Index: 856908 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1304174 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0428. Min Act: -0.0002

Data Index: 418005 (C4 (Web Text))

Max Activating Token Index: 439