Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 376 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2390. Min Act: -0.0005

Data Index: 967747 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2335. Min Act: -0.0005

Data Index: 155681 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2065. Min Act: -0.0005

Data Index: 1151795 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2078. Min Act: -0.0005

Data Index: 455463 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1902. Min Act: -0.0005

Data Index: 210808 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1959. Min Act: -0.0005

Data Index: 1258319 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2031. Min Act: -0.0005

Data Index: 1062442 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2083. Min Act: -0.0005

Data Index: 237719 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2077. Min Act: -0.0005

Data Index: 896356 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1956. Min Act: -0.0005

Data Index: 1315304 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1813. Min Act: -0.0005

Data Index: 205825 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1999. Min Act: -0.0005

Data Index: 868299 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1926. Min Act: -0.0005

Data Index: 1029611 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1921. Min Act: -0.0005

Data Index: 1078463 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1952. Min Act: -0.0005

Data Index: 458761 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1829. Min Act: -0.0005

Data Index: 937432 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1946. Min Act: -0.0005

Data Index: 9614 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1993. Min Act: -0.0005

Data Index: 820242 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1720. Min Act: -0.0005

Data Index: 304809 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1648. Min Act: -0.0005

Data Index: 1355939 (C4 (Web Text))

Max Activating Token Index: 596