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

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

Neuron 4032 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1481850 (Python Code)

Max Activating Token Index: 253

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1618710 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1549769 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1608148 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1607400 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1639581 (Python Code)

Max Activating Token Index: 234

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1605786 (Python Code)

Max Activating Token Index: 678

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1570842 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1543770 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1511084 (Python Code)

Max Activating Token Index: 294

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1650354 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1471524 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1385434 (Python Code)

Max Activating Token Index: 478

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1642934 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1518431 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1416298 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1602549 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1499540 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1460781 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1628330 (Python Code)

Max Activating Token Index: 156