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

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

Neuron 1272 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0058. Min Range: -8.0058

Max Act: 8.0058. Min Act: -0.0000

Data Index: 1569013 (Python Code)

Max Activating Token Index: 946

Text #1

Max Range: 8.0058. Min Range: -8.0058

Max Act: 7.1347. Min Act: -0.0000

Data Index: 1471511 (Python Code)

Max Activating Token Index: 682

Text #2

Max Range: 8.0058. Min Range: -8.0058

Max Act: 7.2984. Min Act: -0.0000

Data Index: 1545167 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 8.0058. Min Range: -8.0058

Max Act: 7.0081. Min Act: -0.0000

Data Index: 1457467 (Python Code)

Max Activating Token Index: 555

Text #4

Max Range: 8.0058. Min Range: -8.0058

Max Act: 7.1528. Min Act: -0.0000

Data Index: 1649649 (Python Code)

Max Activating Token Index: 230

Text #5

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.9399. Min Act: -0.0000

Data Index: 1444127 (Python Code)

Max Activating Token Index: 771

Text #6

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.4801. Min Act: -0.0000

Data Index: 1599409 (Python Code)

Max Activating Token Index: 166

Text #7

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.7373. Min Act: -0.0000

Data Index: 1514227 (Python Code)

Max Activating Token Index: 396

Text #8

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.8018. Min Act: -0.0000

Data Index: 1638280 (Python Code)

Max Activating Token Index: 781

Text #9

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.7614. Min Act: -0.0000

Data Index: 1517377 (Python Code)

Max Activating Token Index: 626

Text #10

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.3037. Min Act: -0.0000

Data Index: 1387534 (Python Code)

Max Activating Token Index: 521

Text #11

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.6785. Min Act: -0.0000

Data Index: 1591953 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 8.0058. Min Range: -8.0058

Max Act: 5.8684. Min Act: -0.0000

Data Index: 1553532 (Python Code)

Max Activating Token Index: 352

Text #13

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.1690. Min Act: -0.0000

Data Index: 1605377 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.5316. Min Act: -0.0000

Data Index: 1449479 (Python Code)

Max Activating Token Index: 435

Text #15

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.1741. Min Act: -0.0000

Data Index: 1459083 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.3717. Min Act: -0.0000

Data Index: 1480934 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 8.0058. Min Range: -8.0058

Max Act: 5.7345. Min Act: -0.0000

Data Index: 1652536 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.2517. Min Act: -0.0000

Data Index: 1447179 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 8.0058. Min Range: -8.0058

Max Act: 6.2521. Min Act: -0.0000

Data Index: 1501595 (Python Code)

Max Activating Token Index: 126