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

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

Neuron 3530 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.5407. Min Act: -0.0001

Data Index: 1378658 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.4792. Min Act: -0.0000

Data Index: 1611920 (Python Code)

Max Activating Token Index: 416

Text #2

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.4343. Min Act: -0.0000

Data Index: 1439457 (Python Code)

Max Activating Token Index: 357

Text #3

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.3955. Min Act: -0.0000

Data Index: 1439270 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1464973 (Python Code)

Max Activating Token Index: 792

Text #5

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.4059. Min Act: -0.0000

Data Index: 1610109 (Python Code)

Max Activating Token Index: 704

Text #6

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.3939. Min Act: -0.0001

Data Index: 1602143 (Python Code)

Max Activating Token Index: 604

Text #7

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.2754. Min Act: -0.0001

Data Index: 1576814 (Python Code)

Max Activating Token Index: 951

Text #8

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.2733. Min Act: -0.0000

Data Index: 1416491 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1472039 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1364383 (Python Code)

Max Activating Token Index: 660

Text #11

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.2194. Min Act: -0.0000

Data Index: 1461614 (Python Code)

Max Activating Token Index: 457

Text #12

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.1738. Min Act: -0.0001

Data Index: 1414006 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.1688. Min Act: -0.0001

Data Index: 1544300 (Python Code)

Max Activating Token Index: 394

Text #14

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.2021. Min Act: -0.0001

Data Index: 1393245 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.2345. Min Act: -0.0000

Data Index: 1644610 (Python Code)

Max Activating Token Index: 510

Text #16

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1364761 (Python Code)

Max Activating Token Index: 595

Text #17

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.1944. Min Act: -0.0000

Data Index: 1513572 (Python Code)

Max Activating Token Index: 475

Text #18

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.1907. Min Act: -0.0001

Data Index: 1585398 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 1.5407. Min Range: -1.5407

Max Act: 1.1405. Min Act: -0.0001

Data Index: 1463134 (Python Code)

Max Activating Token Index: 632