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

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

Neuron 1147 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: 2.7116. Min Range: -2.7116

Max Act: 2.7116. Min Act: -0.0000

Data Index: 1328481 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 2.7116. Min Range: -2.7116

Max Act: 2.6922. Min Act: -0.0000

Data Index: 1072313 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 2.7116. Min Range: -2.7116

Max Act: 2.5711. Min Act: -0.0000

Data Index: 229021 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 2.7116. Min Range: -2.7116

Max Act: 2.1960. Min Act: -0.0000

Data Index: 245134 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 2.7116. Min Range: -2.7116

Max Act: 2.1826. Min Act: -0.0000

Data Index: 761184 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.7116. Min Range: -2.7116

Max Act: 2.1804. Min Act: -0.0000

Data Index: 207019 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 2.7116. Min Range: -2.7116

Max Act: 2.1475. Min Act: -0.0000

Data Index: 164402 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 2.7116. Min Range: -2.7116

Max Act: 2.0694. Min Act: -0.0000

Data Index: 1086177 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.9271. Min Act: -0.0000

Data Index: 106372 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 2.7116. Min Range: -2.7116

Max Act: 2.0366. Min Act: -0.0000

Data Index: 669443 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 2.7116. Min Range: -2.7116

Max Act: 2.0106. Min Act: -0.0000

Data Index: 1190847 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.9690. Min Act: -0.0000

Data Index: 1211507 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.9101. Min Act: -0.0000

Data Index: 710229 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.9848. Min Act: -0.0000

Data Index: 432745 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.8781. Min Act: -0.0000

Data Index: 318484 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.8653. Min Act: -0.0000

Data Index: 872726 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.8542. Min Act: -0.0000

Data Index: 724305 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.9122. Min Act: -0.0000

Data Index: 95710 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.7212. Min Act: -0.0000

Data Index: 1183844 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 2.7116. Min Range: -2.7116

Max Act: 1.8205. Min Act: -0.0000

Data Index: 1004569 (C4 (Web Text))

Max Activating Token Index: 99