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

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

Neuron 5095 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1544445 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1539070 (Python Code)

Max Activating Token Index: 636

Text #2

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1576186 (Python Code)

Max Activating Token Index: 446

Text #3

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1471534 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1465770 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1515367 (Python Code)

Max Activating Token Index: 1016

Text #6

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3714. Min Act: 0.0000

Data Index: 1481554 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1484807 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3635. Min Act: 0.0000

Data Index: 1412843 (Python Code)

Max Activating Token Index: 586

Text #9

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1382098 (Python Code)

Max Activating Token Index: 669

Text #10

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1619557 (Python Code)

Max Activating Token Index: 897

Text #11

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1630176 (Python Code)

Max Activating Token Index: 244

Text #12

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1421334 (Python Code)

Max Activating Token Index: 984

Text #13

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1441544 (Python Code)

Max Activating Token Index: 209

Text #14

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1361520 (Python Code)

Max Activating Token Index: 566

Text #15

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1480931 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1403983 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1568606 (Python Code)

Max Activating Token Index: 215

Text #18

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3217. Min Act: 0.0000

Data Index: 1609613 (Python Code)

Max Activating Token Index: 485

Text #19

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1607347 (Python Code)

Max Activating Token Index: 654