Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4745 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1646936 (Python Code)

Max Activating Token Index: 916

Text #1

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3751. Min Act: -0.0000

Data Index: 1511617 (Python Code)

Max Activating Token Index: 945

Text #2

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1578623 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1590238 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1373879 (Python Code)

Max Activating Token Index: 986

Text #5

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3367. Min Act: -0.0000

Data Index: 1580793 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1469018 (Python Code)

Max Activating Token Index: 944

Text #7

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3127. Min Act: -0.0000

Data Index: 1545135 (Python Code)

Max Activating Token Index: 364

Text #8

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1421739 (Python Code)

Max Activating Token Index: 994

Text #9

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1617204 (Python Code)

Max Activating Token Index: 379

Text #10

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1718. Min Act: -0.0000

Data Index: 1597352 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1523. Min Act: -0.0000

Data Index: 1424311 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1744. Min Act: -0.0000

Data Index: 1601204 (Python Code)

Max Activating Token Index: 961

Text #13

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1070. Min Act: -0.0000

Data Index: 1507537 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1361624 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1433152 (Python Code)

Max Activating Token Index: 350

Text #16

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1461461 (Python Code)

Max Activating Token Index: 777

Text #17

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1449465 (Python Code)

Max Activating Token Index: 120

Text #18

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1422973 (Python Code)

Max Activating Token Index: 890

Text #19

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1478275 (Python Code)

Max Activating Token Index: 344