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

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

Neuron 1131 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.8789. Min Act: -0.0000

Data Index: 965012 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7737. Min Act: -0.0001

Data Index: 1364579 (Python Code)

Max Activating Token Index: 594

Text #2

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7666. Min Act: -0.0001

Data Index: 1616146 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7269. Min Act: -0.0000

Data Index: 179488 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1363158 (Python Code)

Max Activating Token Index: 586

Text #5

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1476448 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1645891 (Python Code)

Max Activating Token Index: 239

Text #7

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1517051 (Python Code)

Max Activating Token Index: 567

Text #8

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1472195 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1626627 (Python Code)

Max Activating Token Index: 133

Text #10

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1593188 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5643. Min Act: -0.0001

Data Index: 1370748 (Python Code)

Max Activating Token Index: 157

Text #12

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1484957 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1630915 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1506453 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1502952 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5073. Min Act: -0.0001

Data Index: 217950 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5501. Min Act: -0.0000

Data Index: 195948 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5843. Min Act: -0.0001

Data Index: 1646957 (Python Code)

Max Activating Token Index: 935

Text #19

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.5694. Min Act: -0.0001

Data Index: 1499239 (Python Code)

Max Activating Token Index: 652