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

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

Neuron 2304 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.1969. Min Act: -0.0000

Data Index: 1365724 (Python Code)

Max Activating Token Index: 734

Text #1

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1565284 (Python Code)

Max Activating Token Index: 704

Text #2

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.8828. Min Act: -0.0000

Data Index: 1428333 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.7243. Min Act: -0.0000

Data Index: 1592781 (Python Code)

Max Activating Token Index: 977

Text #4

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.6446. Min Act: -0.0000

Data Index: 1550950 (Python Code)

Max Activating Token Index: 1012

Text #5

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.6245. Min Act: -0.0000

Data Index: 1515799 (Python Code)

Max Activating Token Index: 599

Text #6

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.7133. Min Act: -0.0000

Data Index: 1478794 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.8044. Min Act: -0.0000

Data Index: 1406078 (Python Code)

Max Activating Token Index: 555

Text #8

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1476949 (Python Code)

Max Activating Token Index: 725

Text #9

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.6532. Min Act: -0.0000

Data Index: 1620064 (Python Code)

Max Activating Token Index: 492

Text #10

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.5375. Min Act: -0.0000

Data Index: 1552642 (Python Code)

Max Activating Token Index: 368

Text #11

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.5349. Min Act: -0.0000

Data Index: 1429824 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.4204. Min Act: -0.0000

Data Index: 1418274 (Python Code)

Max Activating Token Index: 996

Text #13

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1403145 (Python Code)

Max Activating Token Index: 418

Text #14

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1530130 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.5724. Min Act: -0.0000

Data Index: 1533604 (Python Code)

Max Activating Token Index: 305

Text #16

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1510854 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.5448. Min Act: -0.0000

Data Index: 1404711 (Python Code)

Max Activating Token Index: 190

Text #18

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.6310. Min Act: -0.0000

Data Index: 1522798 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 2.1969. Min Range: -2.1969

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1513141 (Python Code)

Max Activating Token Index: 700