Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2231 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3667. Min Act: -0.0001

Data Index: 1558789 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3352. Min Act: -0.0001

Data Index: 1389124 (Python Code)

Max Activating Token Index: 116

Text #2

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3227. Min Act: -0.0001

Data Index: 1456844 (Python Code)

Max Activating Token Index: 138

Text #3

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3092. Min Act: -0.0001

Data Index: 1544536 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3089. Min Act: -0.0001

Data Index: 1382445 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1505860 (Python Code)

Max Activating Token Index: 121

Text #6

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2955. Min Act: -0.0001

Data Index: 1551542 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2945. Min Act: -0.0001

Data Index: 1600756 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1454958 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2763. Min Act: -0.0001

Data Index: 1498388 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1459824 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2739. Min Act: -0.0001

Data Index: 1493694 (Python Code)

Max Activating Token Index: 31

Text #12

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2895. Min Act: -0.0001

Data Index: 1484052 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2702. Min Act: -0.0001

Data Index: 1391764 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2802. Min Act: -0.0001

Data Index: 1450168 (Python Code)

Max Activating Token Index: 790

Text #15

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2707. Min Act: -0.0001

Data Index: 1617031 (Python Code)

Max Activating Token Index: 40

Text #16

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2774. Min Act: -0.0001

Data Index: 1624828 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2864. Min Act: -0.0001

Data Index: 1548209 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1521473 (Python Code)

Max Activating Token Index: 302

Text #19

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2562. Min Act: -0.0001

Data Index: 1388951 (Python Code)

Max Activating Token Index: 59