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

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

Neuron 401 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.9210. Min Act: -0.0000

Data Index: 1523962 (Python Code)

Max Activating Token Index: 902

Text #1

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.6251. Min Act: -0.0000

Data Index: 1580329 (Python Code)

Max Activating Token Index: 255

Text #2

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.5053. Min Act: -0.0000

Data Index: 1489630 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.3814. Min Act: -0.0000

Data Index: 370863 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1246459 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.2467. Min Act: -0.0000

Data Index: 283842 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.1754. Min Act: -0.0000

Data Index: 1581986 (Python Code)

Max Activating Token Index: 112

Text #7

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1159270 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.2935. Min Act: -0.0000

Data Index: 1436728 (Python Code)

Max Activating Token Index: 147

Text #9

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1615360 (Python Code)

Max Activating Token Index: 194

Text #10

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1193123 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.1837. Min Act: -0.0000

Data Index: 405132 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1368202 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.1686. Min Act: -0.0000

Data Index: 1634111 (Python Code)

Max Activating Token Index: 129

Text #14

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.2240. Min Act: -0.0000

Data Index: 1160561 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1028816 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.1992. Min Act: -0.0000

Data Index: 115979 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1593264 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1376836 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 1.9210. Min Range: -1.9210

Max Act: 1.1716. Min Act: -0.0000

Data Index: 1470714 (Python Code)

Max Activating Token Index: 740