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

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

Neuron 3523 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: 1.0016. Min Range: -1.0016

Max Act: 1.0016. Min Act: -0.0000

Data Index: 301170 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.9125. Min Act: -0.0000

Data Index: 512507 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8983. Min Act: -0.0000

Data Index: 243321 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1150425 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.9234. Min Act: -0.0000

Data Index: 580519 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.9437. Min Act: -0.0000

Data Index: 42374 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8793. Min Act: -0.0000

Data Index: 240682 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1268773 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8353. Min Act: -0.0000

Data Index: 536862 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1021532 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8783. Min Act: -0.0000

Data Index: 230408 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8614. Min Act: -0.0000

Data Index: 79391 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8581. Min Act: -0.0000

Data Index: 931183 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8077. Min Act: -0.0000

Data Index: 677338 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8655. Min Act: -0.0000

Data Index: 397915 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.8109. Min Act: -0.0000

Data Index: 328335 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.7825. Min Act: -0.0000

Data Index: 462755 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.7545. Min Act: -0.0000

Data Index: 293993 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.7984. Min Act: -0.0000

Data Index: 451458 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 1.0016. Min Range: -1.0016

Max Act: 0.7961. Min Act: -0.0000

Data Index: 478803 (C4 (Web Text))

Max Activating Token Index: 640