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

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

Neuron 1565 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.8180. Min Act: -0.0000

Data Index: 744225 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.6036. Min Act: -0.0000

Data Index: 939154 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.3130. Min Act: -0.0000

Data Index: 81208 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.3070. Min Act: -0.0000

Data Index: 225583 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.2024. Min Act: -0.0000

Data Index: 688983 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.2404. Min Act: -0.0000

Data Index: 342195 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1546489 (Python Code)

Max Activating Token Index: 185

Text #7

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.3828. Min Act: -0.0000

Data Index: 487778 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.2996. Min Act: -0.0000

Data Index: 13827 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1292153 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.2841. Min Act: 0.0000

Data Index: 768478 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.2766. Min Act: 0.0000

Data Index: 476969 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1000543 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.1977. Min Act: -0.0000

Data Index: 262611 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1259853 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1152815 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.1837. Min Act: -0.0000

Data Index: 221903 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1281395 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.1089. Min Act: -0.0000

Data Index: 743429 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 1.8180. Min Range: -1.8180

Max Act: 1.1437. Min Act: -0.0000

Data Index: 3530 (C4 (Web Text))

Max Activating Token Index: 35