Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 129 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0562. Min Act: -0.0003

Data Index: 536455 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1299350 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0537. Min Act: -0.0003

Data Index: 39330 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0534. Min Act: -0.0004

Data Index: 145362 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1025155 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1346544 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0526. Min Act: -0.0003

Data Index: 727909 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0512. Min Act: -0.0004

Data Index: 1120158 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0523. Min Act: -0.0003

Data Index: 994058 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0530. Min Act: -0.0004

Data Index: 990444 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0522. Min Act: -0.0003

Data Index: 426867 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0502. Min Act: -0.0003

Data Index: 873850 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0520. Min Act: -0.0003

Data Index: 841140 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0506. Min Act: -0.0004

Data Index: 1089414 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1050595 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1142634 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0490. Min Act: -0.0003

Data Index: 462368 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0497. Min Act: -0.0003

Data Index: 793488 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0497. Min Act: -0.0003

Data Index: 622488 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0504. Min Act: -0.0003

Data Index: 200686 (C4 (Web Text))

Max Activating Token Index: 74