Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1793 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0923. Min Act: 0.0000

Data Index: 267129 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0798. Min Act: -0.0002

Data Index: 498559 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0813. Min Act: -0.0003

Data Index: 1635347 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1106514 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0516. Min Act: -0.0003

Data Index: 536634 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1495287 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0476. Min Act: -0.0002

Data Index: 928863 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1515943 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1018168 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0487. Min Act: -0.0002

Data Index: 126757 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0443. Min Act: -0.0003

Data Index: 895820 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1158353 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0441. Min Act: 0.0005

Data Index: 271220 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0400. Min Act: 0.0002

Data Index: 797514 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1288040 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0476. Min Act: -0.0002

Data Index: 831016 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1565584 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0472. Min Act: -0.0002

Data Index: 814263 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0390. Min Act: -0.0002

Data Index: 129520 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0403. Min Act: -0.0003

Data Index: 227952 (C4 (Web Text))

Max Activating Token Index: 425