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

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

Neuron 1886 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.5616. Min Act: -0.0000

Data Index: 1420736 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1381233 (Python Code)

Max Activating Token Index: 369

Text #2

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1383534 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1567883 (Python Code)

Max Activating Token Index: 421

Text #4

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3894. Min Act: -0.0000

Data Index: 1647929 (Python Code)

Max Activating Token Index: 812

Text #5

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.4036. Min Act: -0.0000

Data Index: 1435399 (Python Code)

Max Activating Token Index: 810

Text #6

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2111. Min Act: -0.0000

Data Index: 1485566 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1522902 (Python Code)

Max Activating Token Index: 767

Text #8

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1459900 (Python Code)

Max Activating Token Index: 553

Text #9

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1512312 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1401552 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1504362 (Python Code)

Max Activating Token Index: 867

Text #12

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1510819 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1465324 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1537557 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1381796 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1489628 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1617986 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1588514 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1394867 (Python Code)

Max Activating Token Index: 505