Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1174 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.6221. Min Act: -0.0000

Data Index: 1299968 (The Pile)

Max Activating Token Index: 423

Text #1

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2615. Min Act: -0.0000

Data Index: 211269 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.1720. Min Act: -0.0000

Data Index: 221967 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2252. Min Act: -0.0000

Data Index: 584236 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1433908 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1327081 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1508777 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1275190 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 1.6221. Min Range: -1.6221

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1471485 (The Pile)

Max Activating Token Index: 235

Text #9

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1723581 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.1126. Min Act: -0.0000

Data Index: 862147 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.0065. Min Act: -0.0000

Data Index: 572215 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 1.6221. Min Range: -1.6221

Max Act: 0.9807. Min Act: -0.0000

Data Index: 600288 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.0411. Min Act: -0.0000

Data Index: 996457 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 1.6221. Min Range: -1.6221

Max Act: 0.9619. Min Act: -0.0000

Data Index: 1647408 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 1.6221. Min Range: -1.6221

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1277094 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 1.6221. Min Range: -1.6221

Max Act: 0.9563. Min Act: -0.0000

Data Index: 914774 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 1.6221. Min Range: -1.6221

Max Act: 0.9614. Min Act: -0.0000

Data Index: 720071 (The Pile)

Max Activating Token Index: 42

Text #18

Max Range: 1.6221. Min Range: -1.6221

Max Act: 0.8339. Min Act: -0.0000

Data Index: 209129 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 1.6221. Min Range: -1.6221

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1265552 (The Pile)

Max Activating Token Index: 823