Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 568 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.2266. Min Act: -0.0001

Data Index: 117055 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.2301. Min Act: -0.0001

Data Index: 525970 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1952. Min Act: -0.0001

Data Index: 304973 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.2003. Min Act: -0.0001

Data Index: 264637 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1145554 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.2023. Min Act: -0.0001

Data Index: 539477 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1945. Min Act: -0.0001

Data Index: 923285 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1044576 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1997. Min Act: -0.0001

Data Index: 226454 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1864. Min Act: -0.0001

Data Index: 105223 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1178384 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1980. Min Act: -0.0001

Data Index: 822762 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1894. Min Act: -0.0001

Data Index: 709566 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1732. Min Act: -0.0001

Data Index: 795274 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1792. Min Act: -0.0001

Data Index: 217825 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1721. Min Act: -0.0001

Data Index: 264916 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1716. Min Act: -0.0001

Data Index: 753274 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1765. Min Act: -0.0001

Data Index: 124618 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1823. Min Act: -0.0001

Data Index: 808033 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.2301. Min Range: -0.2301

Max Act: 0.1756. Min Act: -0.0001

Data Index: 805658 (C4 (Web Text))

Max Activating Token Index: 656