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

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

Neuron 4227 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0111. Min Range: -2.0111

Max Act: 2.0111. Min Act: -0.0000

Data Index: 67566 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.7496. Min Act: -0.0000

Data Index: 1181800 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.3985. Min Act: -0.0000

Data Index: 87216 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.7211. Min Act: -0.0000

Data Index: 16864 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.4938. Min Act: -0.0000

Data Index: 1268249 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.4234. Min Act: 0.0000

Data Index: 36089 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1164879 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.3925. Min Act: -0.0000

Data Index: 1125605 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.3733. Min Act: -0.0000

Data Index: 703235 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.2563. Min Act: -0.0000

Data Index: 1107209 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.3578. Min Act: 0.0000

Data Index: 89403 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1060885 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.3151. Min Act: -0.0000

Data Index: 280037 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.3115. Min Act: 0.0000

Data Index: 104255 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1021957 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.1768. Min Act: -0.0000

Data Index: 643023 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.1800. Min Act: -0.0000

Data Index: 974325 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.2413. Min Act: -0.0000

Data Index: 537595 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1245624 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 2.0111. Min Range: -2.0111

Max Act: 1.2383. Min Act: -0.0000

Data Index: 217158 (C4 (Web Text))

Max Activating Token Index: 812