Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4260 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4850. Min Act: -0.0000

Data Index: 764657 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4638. Min Act: 0.0000

Data Index: 537688 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4564. Min Act: -0.0000

Data Index: 474011 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4554. Min Act: -0.0000

Data Index: 983596 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4525. Min Act: 0.0000

Data Index: 1282651 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4167. Min Act: 0.0000

Data Index: 197595 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4588. Min Act: -0.0000

Data Index: 643318 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4311. Min Act: 0.0001

Data Index: 193362 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4155. Min Act: 0.0000

Data Index: 522811 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1025822 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.3946. Min Act: 0.0000

Data Index: 1280742 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.3832. Min Act: -0.0000

Data Index: 857316 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.3992. Min Act: -0.0000

Data Index: 409759 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4063. Min Act: 0.0001

Data Index: 1079041 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.3905. Min Act: -0.0000

Data Index: 216689 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.4052. Min Act: -0.0000

Data Index: 944008 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.3898. Min Act: -0.0000

Data Index: 738407 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.3826. Min Act: 0.0002

Data Index: 663939 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1107041 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.4850. Min Range: -0.4850

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1141810 (C4 (Web Text))

Max Activating Token Index: 64