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

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

Neuron 1521 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.6999. Min Act: -0.0001

Data Index: 758488 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.6845. Min Act: -0.0001

Data Index: 1652731 (Python Code)

Max Activating Token Index: 926

Text #2

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.5484. Min Act: -0.0001

Data Index: 1489750 (Python Code)

Max Activating Token Index: 838

Text #3

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.5326. Min Act: -0.0000

Data Index: 1408298 (Python Code)

Max Activating Token Index: 832

Text #4

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.4393. Min Act: -0.0001

Data Index: 1375684 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.6124. Min Act: -0.0001

Data Index: 182929 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.3263. Min Act: -0.0001

Data Index: 860136 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.4691. Min Act: -0.0000

Data Index: 1608020 (Python Code)

Max Activating Token Index: 100

Text #8

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.3676. Min Act: -0.0001

Data Index: 1509362 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.4488. Min Act: -0.0001

Data Index: 1596115 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.4229. Min Act: -0.0001

Data Index: 1634780 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.4606. Min Act: -0.0001

Data Index: 1447321 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.3418. Min Act: -0.0001

Data Index: 1559137 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.3545. Min Act: -0.0001

Data Index: 1578722 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.2078. Min Act: -0.0001

Data Index: 1416931 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.3586. Min Act: -0.0001

Data Index: 84943 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.3315. Min Act: -0.0001

Data Index: 1455547 (Python Code)

Max Activating Token Index: 261

Text #17

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1613341 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.3018. Min Act: -0.0001

Data Index: 1379824 (Python Code)

Max Activating Token Index: 586

Text #19

Max Range: 1.6999. Min Range: -1.6999

Max Act: 1.4244. Min Act: -0.0001

Data Index: 1616675 (Python Code)

Max Activating Token Index: 718