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

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

Neuron 4977 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.7729. Min Act: -0.0000

Data Index: 1492876 (Python Code)

Max Activating Token Index: 103

Text #1

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6865. Min Act: -0.0000

Data Index: 1494563 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6274. Min Act: -0.0000

Data Index: 1638532 (Python Code)

Max Activating Token Index: 679

Text #3

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.5564. Min Act: -0.0000

Data Index: 1468149 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.2026. Min Act: 0.0000

Data Index: 1635237 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.1792. Min Act: 0.0000

Data Index: 1390968 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.0129. Min Act: -0.0000

Data Index: 1426845 (Python Code)

Max Activating Token Index: 958

Text #7

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.8939. Min Act: 0.0000

Data Index: 1538059 (Python Code)

Max Activating Token Index: 74

Text #8

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.8114. Min Act: -0.0000

Data Index: 1495372 (Python Code)

Max Activating Token Index: 783

Text #9

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.6165. Min Act: 0.0000

Data Index: 1649931 (Python Code)

Max Activating Token Index: 520

Text #10

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.6999. Min Act: -0.0000

Data Index: 1563875 (Python Code)

Max Activating Token Index: 558

Text #11

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.6108. Min Act: 0.0000

Data Index: 1454620 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.5959. Min Act: 0.0000

Data Index: 1491280 (Python Code)

Max Activating Token Index: 663

Text #13

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.5833. Min Act: 0.0000

Data Index: 1403904 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.6795. Min Act: 0.0000

Data Index: 1498817 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.6019. Min Act: -0.0000

Data Index: 1606775 (Python Code)

Max Activating Token Index: 771

Text #16

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.4438. Min Act: 0.0000

Data Index: 1627168 (Python Code)

Max Activating Token Index: 302

Text #17

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.3824. Min Act: 0.0000

Data Index: 1454345 (Python Code)

Max Activating Token Index: 854

Text #18

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.3186. Min Act: 0.0000

Data Index: 1451934 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 3.7729. Min Range: -3.7729

Max Act: 2.1911. Min Act: 0.0000

Data Index: 1401654 (Python Code)

Max Activating Token Index: 62