Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1000 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0445. Min Act: -0.0004

Data Index: 455092 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0403. Min Act: -0.0004

Data Index: 894078 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0004

Data Index: 1041386 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0429. Min Act: -0.0004

Data Index: 737476 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0394. Min Act: -0.0004

Data Index: 740490 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0420. Min Act: -0.0004

Data Index: 111733 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0411. Min Act: -0.0004

Data Index: 1634723 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0426. Min Act: -0.0004

Data Index: 312926 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0400. Min Act: -0.0004

Data Index: 995543 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0392. Min Act: -0.0004

Data Index: 237673 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0370. Min Act: -0.0004

Data Index: 84544 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0393. Min Act: -0.0004

Data Index: 1063220 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0393. Min Act: -0.0004

Data Index: 1023575 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0424. Min Act: -0.0004

Data Index: 29546 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0382. Min Act: -0.0004

Data Index: 594031 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0392. Min Act: -0.0004

Data Index: 744666 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0336. Min Act: -0.0004

Data Index: 509896 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0389. Min Act: -0.0004

Data Index: 169049 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0369. Min Act: -0.0004

Data Index: 1436665 (Python Code)

Max Activating Token Index: 412

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0403. Min Act: -0.0004

Data Index: 648174 (C4 (Web Text))

Max Activating Token Index: 5