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

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

Neuron 2015 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1770. Min Act: -0.0003

Data Index: 6655 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1663. Min Act: -0.0003

Data Index: 292698 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1607. Min Act: -0.0003

Data Index: 773637 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1594. Min Act: -0.0003

Data Index: 318238 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1516. Min Act: -0.0003

Data Index: 295703 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1550. Min Act: -0.0003

Data Index: 406367 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1541. Min Act: -0.0003

Data Index: 264156 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1551. Min Act: -0.0003

Data Index: 366591 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1541. Min Act: -0.0003

Data Index: 51183 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1517. Min Act: -0.0003

Data Index: 534445 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1471. Min Act: -0.0003

Data Index: 547061 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1490. Min Act: -0.0003

Data Index: 286187 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1489. Min Act: -0.0003

Data Index: 534105 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1497. Min Act: -0.0003

Data Index: 629016 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1485. Min Act: -0.0003

Data Index: 181054 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1477. Min Act: -0.0003

Data Index: 217069 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1449. Min Act: -0.0003

Data Index: 405113 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1405. Min Act: -0.0003

Data Index: 64093 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1452. Min Act: -0.0003

Data Index: 1113500 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.1770. Min Range: -0.1770

Max Act: 0.1453. Min Act: -0.0003

Data Index: 787276 (C4 (Web Text))

Max Activating Token Index: 211