Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5660 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0605. Min Range: -5.0605

Max Act: 5.0605. Min Act: -0.0000

Data Index: 1373141 (Python Code)

Max Activating Token Index: 715

Text #1

Max Range: 5.0605. Min Range: -5.0605

Max Act: 4.9143. Min Act: -0.0000

Data Index: 1372763 (Python Code)

Max Activating Token Index: 218

Text #2

Max Range: 5.0605. Min Range: -5.0605

Max Act: 4.8966. Min Act: -0.0000

Data Index: 1366054 (Python Code)

Max Activating Token Index: 658

Text #3

Max Range: 5.0605. Min Range: -5.0605

Max Act: 4.5331. Min Act: -0.0000

Data Index: 1553351 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 5.0605. Min Range: -5.0605

Max Act: 5.0507. Min Act: -0.0000

Data Index: 1587418 (Python Code)

Max Activating Token Index: 881

Text #5

Max Range: 5.0605. Min Range: -5.0605

Max Act: 4.5594. Min Act: -0.0000

Data Index: 1569021 (Python Code)

Max Activating Token Index: 428

Text #6

Max Range: 5.0605. Min Range: -5.0605

Max Act: 4.7127. Min Act: -0.0000

Data Index: 1644257 (Python Code)

Max Activating Token Index: 223

Text #7

Max Range: 5.0605. Min Range: -5.0605

Max Act: 4.3808. Min Act: -0.0000

Data Index: 1475059 (Python Code)

Max Activating Token Index: 244

Text #8

Max Range: 5.0605. Min Range: -5.0605

Max Act: 3.9980. Min Act: -0.0000

Data Index: 1393564 (Python Code)

Max Activating Token Index: 712

Text #9

Max Range: 5.0605. Min Range: -5.0605

Max Act: 3.4340. Min Act: -0.0000

Data Index: 1577977 (Python Code)

Max Activating Token Index: 849

Text #10

Max Range: 5.0605. Min Range: -5.0605

Max Act: 3.6265. Min Act: -0.0000

Data Index: 1434355 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 5.0605. Min Range: -5.0605

Max Act: 3.1303. Min Act: -0.0000

Data Index: 1609282 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 5.0605. Min Range: -5.0605

Max Act: 3.1310. Min Act: -0.0000

Data Index: 1390612 (Python Code)

Max Activating Token Index: 840

Text #13

Max Range: 5.0605. Min Range: -5.0605

Max Act: 2.7216. Min Act: -0.0000

Data Index: 1427455 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 5.0605. Min Range: -5.0605

Max Act: 2.9836. Min Act: -0.0000

Data Index: 1555917 (Python Code)

Max Activating Token Index: 558

Text #15

Max Range: 5.0605. Min Range: -5.0605

Max Act: 3.4124. Min Act: -0.0000

Data Index: 1442982 (Python Code)

Max Activating Token Index: 270

Text #16

Max Range: 5.0605. Min Range: -5.0605

Max Act: 2.9980. Min Act: -0.0000

Data Index: 1455642 (Python Code)

Max Activating Token Index: 488

Text #17

Max Range: 5.0605. Min Range: -5.0605

Max Act: 2.8427. Min Act: -0.0000

Data Index: 1037739 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 5.0605. Min Range: -5.0605

Max Act: 3.0019. Min Act: -0.0000

Data Index: 1395303 (Python Code)

Max Activating Token Index: 707

Text #19

Max Range: 5.0605. Min Range: -5.0605

Max Act: 2.8329. Min Act: -0.0000

Data Index: 1570452 (Python Code)

Max Activating Token Index: 753