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

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

Neuron 1332 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0809. Min Range: -1.0809

Max Act: 1.0760. Min Act: -0.0000

Data Index: 604967 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 1.0809. Min Range: -1.0809

Max Act: 1.0809. Min Act: -0.0000

Data Index: 625652 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1124719 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8983. Min Act: -0.0000

Data Index: 995279 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1251318 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.9999. Min Act: -0.0000

Data Index: 598632 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.9128. Min Act: -0.0000

Data Index: 904990 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.9055. Min Act: -0.0000

Data Index: 615221 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.9292. Min Act: -0.0000

Data Index: 370631 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.9176. Min Act: -0.0000

Data Index: 436231 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8910. Min Act: -0.0000

Data Index: 212689 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1068217 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8607. Min Act: -0.0000

Data Index: 396680 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8603. Min Act: -0.0000

Data Index: 522017 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8750. Min Act: -0.0000

Data Index: 427355 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1348735 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8447. Min Act: -0.0000

Data Index: 462324 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8665. Min Act: -0.0000

Data Index: 369800 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8198. Min Act: -0.0000

Data Index: 956922 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 1.0809. Min Range: -1.0809

Max Act: 0.8727. Min Act: -0.0000

Data Index: 257900 (C4 (Web Text))

Max Activating Token Index: 790