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

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

Neuron 495 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1398449 (Python Code)

Max Activating Token Index: 295

Text #1

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1408667 (Python Code)

Max Activating Token Index: 915

Text #2

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1441386 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1595078 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1527659 (Python Code)

Max Activating Token Index: 896

Text #5

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1412826 (Python Code)

Max Activating Token Index: 691

Text #6

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1389331 (Python Code)

Max Activating Token Index: 475

Text #7

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1568787 (Python Code)

Max Activating Token Index: 386

Text #8

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1619478 (Python Code)

Max Activating Token Index: 925

Text #9

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1390787 (Python Code)

Max Activating Token Index: 479

Text #10

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1563340 (Python Code)

Max Activating Token Index: 317

Text #11

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1390110 (Python Code)

Max Activating Token Index: 683

Text #12

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1516383 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1472182 (Python Code)

Max Activating Token Index: 828

Text #14

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1441321 (Python Code)

Max Activating Token Index: 147

Text #15

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1376803 (Python Code)

Max Activating Token Index: 923

Text #16

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1392407 (Python Code)

Max Activating Token Index: 882

Text #17

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1493110 (Python Code)

Max Activating Token Index: 889

Text #18

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1625509 (Python Code)

Max Activating Token Index: 772

Text #19

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1404187 (Python Code)

Max Activating Token Index: 282