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

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

Neuron 612 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1202. Min Range: -1.1202

Max Act: 1.0132. Min Act: -0.0001

Data Index: 1526047 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 1.1202. Min Range: -1.1202

Max Act: 1.1202. Min Act: -0.0001

Data Index: 1466687 (Python Code)

Max Activating Token Index: 547

Text #2

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9888. Min Act: -0.0001

Data Index: 1416575 (Python Code)

Max Activating Token Index: 513

Text #3

Max Range: 1.1202. Min Range: -1.1202

Max Act: 1.0397. Min Act: -0.0001

Data Index: 1383134 (Python Code)

Max Activating Token Index: 778

Text #4

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9276. Min Act: -0.0001

Data Index: 1650886 (Python Code)

Max Activating Token Index: 775

Text #5

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9953. Min Act: -0.0001

Data Index: 1567311 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9370. Min Act: -0.0001

Data Index: 1644978 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 1.1202. Min Range: -1.1202

Max Act: 1.0480. Min Act: -0.0001

Data Index: 1529711 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9127. Min Act: -0.0001

Data Index: 1511628 (Python Code)

Max Activating Token Index: 605

Text #9

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9555. Min Act: -0.0001

Data Index: 1422662 (Python Code)

Max Activating Token Index: 351

Text #10

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9542. Min Act: -0.0001

Data Index: 1523260 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8216. Min Act: -0.0001

Data Index: 1521046 (Python Code)

Max Activating Token Index: 754

Text #12

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8400. Min Act: -0.0001

Data Index: 1506186 (Python Code)

Max Activating Token Index: 300

Text #13

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8739. Min Act: -0.0001

Data Index: 1506308 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8929. Min Act: -0.0001

Data Index: 1602257 (Python Code)

Max Activating Token Index: 397

Text #15

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9472. Min Act: -0.0001

Data Index: 1442748 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.9406. Min Act: -0.0001

Data Index: 1486245 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8606. Min Act: -0.0001

Data Index: 1472477 (Python Code)

Max Activating Token Index: 696

Text #18

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8028. Min Act: -0.0001

Data Index: 1490063 (Python Code)

Max Activating Token Index: 168

Text #19

Max Range: 1.1202. Min Range: -1.1202

Max Act: 0.8511. Min Act: -0.0001

Data Index: 1484148 (Python Code)

Max Activating Token Index: 406