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

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

Neuron 105 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: 0.0765. Min Range: -0.0765

Max Act: 0.0765. Min Act: -0.0004

Data Index: 1142013 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0498. Min Act: -0.0003

Data Index: 704559 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0464. Min Act: -0.0003

Data Index: 610850 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0433. Min Act: -0.0003

Data Index: 369753 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0449. Min Act: -0.0003

Data Index: 613238 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1328621 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1260757 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0409. Min Act: -0.0003

Data Index: 895431 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0408. Min Act: -0.0003

Data Index: 270807 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0408. Min Act: -0.0003

Data Index: 220877 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0378. Min Act: -0.0003

Data Index: 720017 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0403. Min Act: -0.0003

Data Index: 464727 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0401. Min Act: -0.0003

Data Index: 373095 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0357. Min Act: -0.0003

Data Index: 463126 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0383. Min Act: -0.0004

Data Index: 980325 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0379. Min Act: -0.0003

Data Index: 787553 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0376. Min Act: -0.0003

Data Index: 262643 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1247032 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0400. Min Act: -0.0004

Data Index: 955063 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0357. Min Act: -0.0003

Data Index: 771509 (C4 (Web Text))

Max Activating Token Index: 1003