Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2540 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7830. Min Act: -0.0001

Data Index: 1139842 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7268. Min Act: -0.0001

Data Index: 242100 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7668. Min Act: -0.0001

Data Index: 780242 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6584. Min Act: -0.0001

Data Index: 584241 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6393. Min Act: -0.0001

Data Index: 1352045 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1008642 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6324. Min Act: -0.0001

Data Index: 645419 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7359. Min Act: -0.0001

Data Index: 422797 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6272. Min Act: -0.0001

Data Index: 787184 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6562. Min Act: -0.0001

Data Index: 1265688 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6602. Min Act: -0.0001

Data Index: 897878 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6225. Min Act: -0.0001

Data Index: 529158 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5975. Min Act: -0.0001

Data Index: 994805 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1260703 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1035524 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5435. Min Act: -0.0001

Data Index: 419494 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6285. Min Act: -0.0001

Data Index: 1281573 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6239. Min Act: -0.0001

Data Index: 1241781 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6027. Min Act: -0.0001

Data Index: 158480 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6400. Min Act: -0.0001

Data Index: 160808 (C4 (Web Text))

Max Activating Token Index: 938