Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 529 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.9833. Min Act: -0.0001

Data Index: 1557807 (Python Code)

Max Activating Token Index: 240

Text #1

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.9147. Min Act: -0.0001

Data Index: 1651329 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7494. Min Act: -0.0001

Data Index: 1516132 (Python Code)

Max Activating Token Index: 561

Text #3

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7546. Min Act: -0.0001

Data Index: 1423254 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7466. Min Act: -0.0001

Data Index: 1378340 (Python Code)

Max Activating Token Index: 493

Text #5

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7771. Min Act: -0.0001

Data Index: 1580076 (Python Code)

Max Activating Token Index: 527

Text #6

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7519. Min Act: -0.0001

Data Index: 1556075 (Python Code)

Max Activating Token Index: 589

Text #7

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7414. Min Act: -0.0001

Data Index: 1377603 (Python Code)

Max Activating Token Index: 777

Text #8

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7825. Min Act: -0.0001

Data Index: 1376262 (Python Code)

Max Activating Token Index: 626

Text #9

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7213. Min Act: -0.0001

Data Index: 1523465 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7368. Min Act: -0.0001

Data Index: 1625390 (Python Code)

Max Activating Token Index: 305

Text #11

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7311. Min Act: -0.0001

Data Index: 1441306 (Python Code)

Max Activating Token Index: 308

Text #12

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7720. Min Act: -0.0001

Data Index: 1451437 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7197. Min Act: -0.0001

Data Index: 1477048 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.6416. Min Act: -0.0001

Data Index: 1560453 (Python Code)

Max Activating Token Index: 765

Text #15

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7331. Min Act: -0.0001

Data Index: 1621097 (Python Code)

Max Activating Token Index: 953

Text #16

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.6894. Min Act: -0.0001

Data Index: 1475017 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.6637. Min Act: -0.0001

Data Index: 1564190 (Python Code)

Max Activating Token Index: 575

Text #18

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7287. Min Act: -0.0001

Data Index: 1441312 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.6655. Min Act: -0.0001

Data Index: 1374560 (Python Code)

Max Activating Token Index: 851