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

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

Neuron 1357 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0051. Min Range: -1.0051

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1299950 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.9128. Min Act: -0.0000

Data Index: 412286 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8985. Min Act: -0.0000

Data Index: 594581 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8724. Min Act: -0.0000

Data Index: 657001 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1256953 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1349882 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8301. Min Act: -0.0000

Data Index: 676485 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7882. Min Act: -0.0000

Data Index: 523248 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7827. Min Act: -0.0000

Data Index: 672030 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8009. Min Act: -0.0000

Data Index: 710529 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7707. Min Act: -0.0000

Data Index: 307990 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7493. Min Act: -0.0000

Data Index: 261025 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7536. Min Act: -0.0000

Data Index: 931178 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7722. Min Act: -0.0000

Data Index: 960764 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1039854 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7445. Min Act: -0.0000

Data Index: 7955 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7186. Min Act: -0.0000

Data Index: 137064 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7270. Min Act: -0.0000

Data Index: 937479 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7278. Min Act: -0.0000

Data Index: 874821 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1075661 (C4 (Web Text))

Max Activating Token Index: 953