Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1937 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9850. Min Act: -0.0000

Data Index: 91560 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8609. Min Act: -0.0000

Data Index: 841813 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7822. Min Act: -0.0001

Data Index: 83623 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8004. Min Act: -0.0001

Data Index: 725543 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7822. Min Act: -0.0000

Data Index: 301863 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7759. Min Act: -0.0000

Data Index: 897918 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7859. Min Act: -0.0001

Data Index: 228216 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1038162 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7257. Min Act: -0.0000

Data Index: 727603 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7291. Min Act: -0.0000

Data Index: 555399 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7944. Min Act: -0.0000

Data Index: 311174 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7339. Min Act: -0.0001

Data Index: 23382 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1068055 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.6894. Min Act: -0.0000

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1066019 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7212. Min Act: -0.0000

Data Index: 746980 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7431. Min Act: -0.0001

Data Index: 33209 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1049972 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.6709. Min Act: -0.0000

Data Index: 797991 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.6801. Min Act: -0.0001

Data Index: 1072491 (C4 (Web Text))

Max Activating Token Index: 241