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

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

Neuron 4279 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: 1.1465. Min Range: -1.1465

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1176328 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 1.1465. Min Range: -1.1465

Max Act: 1.1465. Min Act: -0.0000

Data Index: 1417558 (Python Code)

Max Activating Token Index: 727

Text #2

Max Range: 1.1465. Min Range: -1.1465

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1365170 (Python Code)

Max Activating Token Index: 303

Text #3

Max Range: 1.1465. Min Range: -1.1465

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1079283 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.1465. Min Range: -1.1465

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1435448 (Python Code)

Max Activating Token Index: 142

Text #5

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1641002 (Python Code)

Max Activating Token Index: 245

Text #6

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1582053 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1410132 (Python Code)

Max Activating Token Index: 836

Text #8

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1587290 (Python Code)

Max Activating Token Index: 220

Text #9

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1138093 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8928. Min Act: -0.0000

Data Index: 371970 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1314461 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1612464 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9052. Min Act: -0.0000

Data Index: 357947 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1547370 (Python Code)

Max Activating Token Index: 709

Text #15

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1370493 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1141133 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1573298 (Python Code)

Max Activating Token Index: 602

Text #18

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1377525 (Python Code)

Max Activating Token Index: 764

Text #19

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1613755 (Python Code)

Max Activating Token Index: 356