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

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

Neuron 3852 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1496704 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.1761. Min Act: -0.0000

Data Index: 1472998 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.2360. Min Act: -0.0000

Data Index: 1608252 (Python Code)

Max Activating Token Index: 595

Text #3

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1590305 (Python Code)

Max Activating Token Index: 651

Text #4

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1539409 (Python Code)

Max Activating Token Index: 670

Text #5

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.1583. Min Act: -0.0000

Data Index: 1564193 (Python Code)

Max Activating Token Index: 163

Text #6

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.1335. Min Act: -0.0000

Data Index: 1645568 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1423155 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1612271 (Python Code)

Max Activating Token Index: 391

Text #9

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1479031 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1522369 (Python Code)

Max Activating Token Index: 428

Text #11

Max Range: 1.3137. Min Range: -1.3137

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1541927 (Python Code)

Max Activating Token Index: 569

Text #12

Max Range: 1.3137. Min Range: -1.3137

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1507037 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 1.3137. Min Range: -1.3137

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1649389 (Python Code)

Max Activating Token Index: 680

Text #14

Max Range: 1.3137. Min Range: -1.3137

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1512202 (Python Code)

Max Activating Token Index: 301

Text #15

Max Range: 1.3137. Min Range: -1.3137

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1555197 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 1.3137. Min Range: -1.3137

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1441680 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 1.3137. Min Range: -1.3137

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1471890 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 1.3137. Min Range: -1.3137

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1569997 (Python Code)

Max Activating Token Index: 439

Text #19

Max Range: 1.3137. Min Range: -1.3137

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1473424 (Python Code)

Max Activating Token Index: 765