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

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

Neuron 4209 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.2967. Min Act: -0.0000

Data Index: 1358425 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0200. Min Act: -0.0000

Data Index: 224623 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0039. Min Act: -0.0000

Data Index: 465936 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.8504. Min Act: -0.0000

Data Index: 498224 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.8432. Min Act: -0.0000

Data Index: 571243 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.7779. Min Act: -0.0000

Data Index: 247142 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.7771. Min Act: -0.0000

Data Index: 796862 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.8065. Min Act: -0.0000

Data Index: 70178 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1061151 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1087041 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.8059. Min Act: -0.0000

Data Index: 800931 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.8638. Min Act: -0.0000

Data Index: 583750 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.7098. Min Act: -0.0000

Data Index: 643646 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1050333 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.6937. Min Act: -0.0000

Data Index: 218739 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.7098. Min Act: -0.0000

Data Index: 403471 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.6842. Min Act: -0.0000

Data Index: 576951 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1316585 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.6896. Min Act: -0.0000

Data Index: 841633 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.6688. Min Act: -0.0000

Data Index: 63082 (C4 (Web Text))

Max Activating Token Index: 110