Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5822 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9586. Min Act: -0.0002

Data Index: 1606832 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9623. Min Act: -0.0002

Data Index: 1553995 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9284. Min Act: -0.0002

Data Index: 1557611 (Python Code)

Max Activating Token Index: 197

Text #3

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9408. Min Act: -0.0002

Data Index: 1444108 (Python Code)

Max Activating Token Index: 219

Text #4

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9160. Min Act: -0.0002

Data Index: 1432581 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9171. Min Act: -0.0002

Data Index: 1483136 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9049. Min Act: -0.0002

Data Index: 1471902 (Python Code)

Max Activating Token Index: 206

Text #7

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8877. Min Act: -0.0002

Data Index: 1382426 (Python Code)

Max Activating Token Index: 711

Text #8

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8925. Min Act: -0.0002

Data Index: 1555437 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8706. Min Act: -0.0002

Data Index: 1434688 (Python Code)

Max Activating Token Index: 229

Text #10

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8621. Min Act: -0.0002

Data Index: 1383394 (Python Code)

Max Activating Token Index: 729

Text #11

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8685. Min Act: -0.0002

Data Index: 1564219 (Python Code)

Max Activating Token Index: 363

Text #12

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8687. Min Act: -0.0002

Data Index: 1496011 (Python Code)

Max Activating Token Index: 924

Text #13

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8722. Min Act: -0.0002

Data Index: 1374965 (Python Code)

Max Activating Token Index: 196

Text #14

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8471. Min Act: -0.0002

Data Index: 1409499 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8550. Min Act: -0.0002

Data Index: 1373144 (Python Code)

Max Activating Token Index: 630

Text #16

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8598. Min Act: -0.0002

Data Index: 1392751 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8620. Min Act: -0.0002

Data Index: 1445450 (Python Code)

Max Activating Token Index: 767

Text #18

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8423. Min Act: -0.0002

Data Index: 1403782 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8690. Min Act: -0.0002

Data Index: 1495568 (Python Code)

Max Activating Token Index: 202