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

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

Neuron 815 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.6621. Min Act: -0.0000

Data Index: 1544033 (Python Code)

Max Activating Token Index: 830

Text #1

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.6788. Min Act: -0.0000

Data Index: 1551421 (Python Code)

Max Activating Token Index: 533

Text #2

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.2283. Min Act: -0.0000

Data Index: 1567314 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.4303. Min Act: -0.0000

Data Index: 1551718 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.5372. Min Act: -0.0000

Data Index: 1627805 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.3056. Min Act: -0.0000

Data Index: 1365400 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.1832. Min Act: -0.0000

Data Index: 1613325 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.2918. Min Act: -0.0000

Data Index: 1449198 (Python Code)

Max Activating Token Index: 481

Text #8

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0553. Min Act: -0.0000

Data Index: 1646665 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.1318. Min Act: -0.0000

Data Index: 1385668 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.3167. Min Act: -0.0000

Data Index: 1510210 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.2030. Min Act: -0.0000

Data Index: 1587261 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0372. Min Act: -0.0000

Data Index: 1651877 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0047. Min Act: -0.0000

Data Index: 1442964 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 2.6788. Min Range: -2.6788

Max Act: 1.9716. Min Act: -0.0000

Data Index: 1519164 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.1109. Min Act: -0.0000

Data Index: 1620879 (Python Code)

Max Activating Token Index: 635

Text #16

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0504. Min Act: -0.0000

Data Index: 1459520 (Python Code)

Max Activating Token Index: 592

Text #17

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0708. Min Act: -0.0000

Data Index: 1460193 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 2.6788. Min Range: -2.6788

Max Act: 1.7940. Min Act: -0.0000

Data Index: 1604066 (Python Code)

Max Activating Token Index: 36

Text #19

Max Range: 2.6788. Min Range: -2.6788

Max Act: 1.9981. Min Act: -0.0000

Data Index: 1552802 (Python Code)

Max Activating Token Index: 150