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

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

Neuron 2222 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1903. Min Act: -0.0001

Data Index: 602020 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1619. Min Act: -0.0001

Data Index: 943217 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1318729 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1290. Min Act: -0.0001

Data Index: 825247 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1517. Min Act: -0.0001

Data Index: 281586 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1436. Min Act: -0.0001

Data Index: 495532 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1524. Min Act: -0.0001

Data Index: 298194 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1326. Min Act: -0.0001

Data Index: 226616 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1243010 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1195. Min Act: -0.0001

Data Index: 538413 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1225. Min Act: -0.0001

Data Index: 151364 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1015. Min Act: -0.0001

Data Index: 746369 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1117. Min Act: -0.0001

Data Index: 250197 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1245. Min Act: -0.0001

Data Index: 837161 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.0971. Min Act: -0.0001

Data Index: 88459 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1082. Min Act: -0.0001

Data Index: 496588 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.0995. Min Act: -0.0001

Data Index: 218490 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.0946. Min Act: -0.0001

Data Index: 115436 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.0990. Min Act: -0.0001

Data Index: 70166 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1154181 (C4 (Web Text))

Max Activating Token Index: 614