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

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

Neuron 3461 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.3194. Min Act: -0.0000

Data Index: 222877 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1402068 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2437. Min Act: -0.0000

Data Index: 86478 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1635033 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2116. Min Act: -0.0000

Data Index: 168991 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1378580 (Python Code)

Max Activating Token Index: 536

Text #6

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2012. Min Act: -0.0000

Data Index: 440478 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1892. Min Act: 0.0000

Data Index: 951594 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1136144 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1621581 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1129731 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1917. Min Act: 0.0000

Data Index: 435 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1783. Min Act: -0.0000

Data Index: 866733 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1256835 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1335559 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1428941 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1761. Min Act: -0.0000

Data Index: 105653 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1550. Min Act: -0.0000

Data Index: 114173 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1702. Min Act: -0.0000

Data Index: 251377 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1438088 (Python Code)

Max Activating Token Index: 231