Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4613 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1264743 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5782. Min Act: -0.0001

Data Index: 889771 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5431. Min Act: -0.0001

Data Index: 295843 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5264. Min Act: -0.0001

Data Index: 1317409 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4974. Min Act: -0.0000

Data Index: 944167 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4594. Min Act: -0.0001

Data Index: 1156595 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4539. Min Act: -0.0000

Data Index: 995526 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4264. Min Act: -0.0001

Data Index: 234759 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1328430 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4481. Min Act: -0.0000

Data Index: 696127 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4060. Min Act: -0.0001

Data Index: 1097016 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4444. Min Act: -0.0000

Data Index: 791623 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4333. Min Act: -0.0000

Data Index: 839635 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4227. Min Act: -0.0001

Data Index: 914884 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4068. Min Act: -0.0000

Data Index: 458910 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4148. Min Act: -0.0001

Data Index: 622640 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.3980. Min Act: -0.0001

Data Index: 1148733 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4279. Min Act: -0.0001

Data Index: 762442 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.3674. Min Act: -0.0001

Data Index: 626070 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1343100 (C4 (Web Text))

Max Activating Token Index: 556