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

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

Neuron 2531 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.9100. Min Act: -0.0000

Data Index: 633446 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8394. Min Act: -0.0000

Data Index: 359005 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1105940 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8081. Min Act: 0.0000

Data Index: 583330 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7658. Min Act: -0.0000

Data Index: 952966 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7178. Min Act: -0.0000

Data Index: 925281 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7257. Min Act: -0.0000

Data Index: 509098 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1200378 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1057928 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6924. Min Act: -0.0000

Data Index: 385872 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6712. Min Act: -0.0000

Data Index: 738908 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6584. Min Act: -0.0000

Data Index: 600079 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6699. Min Act: -0.0000

Data Index: 435831 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6461. Min Act: -0.0000

Data Index: 280003 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6390. Min Act: -0.0000

Data Index: 229878 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6242. Min Act: -0.0000

Data Index: 395204 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6080. Min Act: -0.0000

Data Index: 259279 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6205. Min Act: -0.0000

Data Index: 2022 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6403. Min Act: -0.0000

Data Index: 940201 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6164. Min Act: -0.0000

Data Index: 874599 (C4 (Web Text))

Max Activating Token Index: 132