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

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

Neuron 1392 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.4133. Min Act: -0.0000

Data Index: 1482278 (Python Code)

Max Activating Token Index: 452

Text #1

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.6589. Min Act: -0.0000

Data Index: 1650772 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.8089. Min Act: -0.0000

Data Index: 1629122 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.3783. Min Act: -0.0000

Data Index: 1545551 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.2328. Min Act: -0.0000

Data Index: 1410802 (Python Code)

Max Activating Token Index: 482

Text #5

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.4728. Min Act: -0.0000

Data Index: 1387137 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.2732. Min Act: -0.0000

Data Index: 1449154 (Python Code)

Max Activating Token Index: 855

Text #7

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.4184. Min Act: -0.0000

Data Index: 1584938 (Python Code)

Max Activating Token Index: 721

Text #8

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.2544. Min Act: -0.0000

Data Index: 1498225 (Python Code)

Max Activating Token Index: 51

Text #9

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.1143. Min Act: -0.0000

Data Index: 1531757 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.3332. Min Act: -0.0000

Data Index: 1550570 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.2904. Min Act: -0.0000

Data Index: 1532982 (Python Code)

Max Activating Token Index: 951

Text #12

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.2830. Min Act: -0.0001

Data Index: 1599857 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.3933. Min Act: -0.0000

Data Index: 1567070 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.2630. Min Act: -0.0000

Data Index: 1462192 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.1414. Min Act: -0.0000

Data Index: 1368179 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.1346. Min Act: -0.0000

Data Index: 1498298 (Python Code)

Max Activating Token Index: 49

Text #17

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.2100. Min Act: -0.0000

Data Index: 1535998 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.0520. Min Act: -0.0000

Data Index: 1501225 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 3.4133. Min Range: -3.4133

Max Act: 2.1220. Min Act: -0.0000

Data Index: 1479388 (Python Code)

Max Activating Token Index: 55