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

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

Neuron 4788 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.2526. Min Act: -0.0000

Data Index: 371403 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.3271. Min Act: -0.0000

Data Index: 904368 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1719. Min Act: -0.0000

Data Index: 385514 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0908. Min Act: -0.0000

Data Index: 625964 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1359447 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1352892 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0890. Min Act: -0.0000

Data Index: 696037 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9455. Min Act: -0.0000

Data Index: 339389 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8111. Min Act: -0.0000

Data Index: 4907 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9753. Min Act: -0.0000

Data Index: 286933 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9642. Min Act: -0.0000

Data Index: 228538 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1238734 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9228. Min Act: -0.0000

Data Index: 62626 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8992. Min Act: -0.0000

Data Index: 35643 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8279. Min Act: -0.0000

Data Index: 149280 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9374. Min Act: -0.0000

Data Index: 969729 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1031812 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.7879. Min Act: -0.0000

Data Index: 833778 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8668. Min Act: -0.0000

Data Index: 200721 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.7846. Min Act: -0.0000

Data Index: 883217 (C4 (Web Text))

Max Activating Token Index: 147