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

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

Neuron 3704 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0449. Min Range: -5.0449

Max Act: 5.0449. Min Act: -0.0000

Data Index: 1587313 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.8330. Min Act: -0.0000

Data Index: 1641852 (Python Code)

Max Activating Token Index: 433

Text #2

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.9903. Min Act: -0.0000

Data Index: 1370478 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.8057. Min Act: -0.0000

Data Index: 1581588 (Python Code)

Max Activating Token Index: 152

Text #4

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.7669. Min Act: -0.0000

Data Index: 1626832 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.4289. Min Act: -0.0000

Data Index: 1606516 (Python Code)

Max Activating Token Index: 264

Text #6

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.5110. Min Act: -0.0000

Data Index: 1406954 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.3058. Min Act: -0.0000

Data Index: 1428627 (Python Code)

Max Activating Token Index: 618

Text #8

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.4615. Min Act: -0.0000

Data Index: 1539424 (Python Code)

Max Activating Token Index: 925

Text #9

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.4703. Min Act: -0.0000

Data Index: 1496923 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.1106. Min Act: -0.0000

Data Index: 1430801 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.4397. Min Act: -0.0000

Data Index: 1370652 (Python Code)

Max Activating Token Index: 649

Text #12

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.3700. Min Act: -0.0000

Data Index: 1392822 (Python Code)

Max Activating Token Index: 1011

Text #13

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.3444. Min Act: -0.0000

Data Index: 1437790 (Python Code)

Max Activating Token Index: 394

Text #14

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.3029. Min Act: -0.0000

Data Index: 1382612 (Python Code)

Max Activating Token Index: 97

Text #15

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.0730. Min Act: -0.0000

Data Index: 1377903 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 5.0449. Min Range: -5.0449

Max Act: 3.8831. Min Act: -0.0000

Data Index: 1377660 (Python Code)

Max Activating Token Index: 885

Text #17

Max Range: 5.0449. Min Range: -5.0449

Max Act: 3.8787. Min Act: -0.0000

Data Index: 1647001 (Python Code)

Max Activating Token Index: 429

Text #18

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.0439. Min Act: -0.0000

Data Index: 1391901 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 5.0449. Min Range: -5.0449

Max Act: 3.8550. Min Act: -0.0000

Data Index: 1478432 (Python Code)

Max Activating Token Index: 272