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

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

Neuron 3946 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1524601 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1626944 (Python Code)

Max Activating Token Index: 565

Text #2

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1410367 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1459480 (Python Code)

Max Activating Token Index: 226

Text #4

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1599506 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1427359 (Python Code)

Max Activating Token Index: 215

Text #6

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1437836 (Python Code)

Max Activating Token Index: 361

Text #7

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1596197 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1375635 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1603966 (Python Code)

Max Activating Token Index: 91

Text #10

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1380998 (Python Code)

Max Activating Token Index: 642

Text #11

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1412776 (Python Code)

Max Activating Token Index: 408

Text #12

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1459769 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1619568 (Python Code)

Max Activating Token Index: 951

Text #14

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1553835 (Python Code)

Max Activating Token Index: 655

Text #15

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1430646 (Python Code)

Max Activating Token Index: 1020

Text #16

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1390116 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1640327 (Python Code)

Max Activating Token Index: 786

Text #18

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1638174 (Python Code)

Max Activating Token Index: 539

Text #19

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1367574 (Python Code)

Max Activating Token Index: 929