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

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

Neuron 1162 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.3560. Min Act: -0.0000

Data Index: 1387115 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.4584. Min Act: -0.0000

Data Index: 1646214 (Python Code)

Max Activating Token Index: 343

Text #2

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.2901. Min Act: -0.0000

Data Index: 1484290 (Python Code)

Max Activating Token Index: 38

Text #3

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.1391. Min Act: -0.0000

Data Index: 1470309 (Python Code)

Max Activating Token Index: 414

Text #4

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.0470. Min Act: -0.0000

Data Index: 1574087 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.1615. Min Act: -0.0000

Data Index: 1644897 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.2735. Min Act: -0.0000

Data Index: 1513503 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.3024. Min Act: -0.0000

Data Index: 1533350 (Python Code)

Max Activating Token Index: 643

Text #8

Max Range: 2.4584. Min Range: -2.4584

Max Act: 1.9196. Min Act: -0.0000

Data Index: 1566353 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.0381. Min Act: -0.0000

Data Index: 1635816 (Python Code)

Max Activating Token Index: 695

Text #10

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.1218. Min Act: -0.0000

Data Index: 1581901 (Python Code)

Max Activating Token Index: 620

Text #11

Max Range: 2.4584. Min Range: -2.4584

Max Act: 1.9678. Min Act: -0.0000

Data Index: 1623078 (Python Code)

Max Activating Token Index: 1001

Text #12

Max Range: 2.4584. Min Range: -2.4584

Max Act: 2.0667. Min Act: -0.0000

Data Index: 1607681 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 2.4584. Min Range: -2.4584

Max Act: 1.8560. Min Act: -0.0000

Data Index: 1583615 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 2.4584. Min Range: -2.4584

Max Act: 1.9516. Min Act: -0.0000

Data Index: 1501777 (Python Code)

Max Activating Token Index: 332

Text #15

Max Range: 2.4584. Min Range: -2.4584

Max Act: 1.8781. Min Act: -0.0000

Data Index: 1575792 (Python Code)

Max Activating Token Index: 875

Text #16

Max Range: 2.4584. Min Range: -2.4584

Max Act: 1.8973. Min Act: -0.0000

Data Index: 1537966 (Python Code)

Max Activating Token Index: 254

Text #17

Max Range: 2.4584. Min Range: -2.4584

Max Act: 1.9706. Min Act: -0.0000

Data Index: 1571895 (Python Code)

Max Activating Token Index: 215

Text #18

Max Range: 2.4584. Min Range: -2.4584

Max Act: 1.8634. Min Act: -0.0000

Data Index: 1582413 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.4584. Min Range: -2.4584

Max Act: 1.8452. Min Act: -0.0000

Data Index: 1413636 (Python Code)

Max Activating Token Index: 47