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

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

Neuron 999 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2467. Min Act: -0.0001

Data Index: 152561 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1124263 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2370. Min Act: -0.0001

Data Index: 891311 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2186. Min Act: -0.0001

Data Index: 637863 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1170672 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2197. Min Act: -0.0001

Data Index: 607873 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2018. Min Act: -0.0001

Data Index: 511782 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2107. Min Act: -0.0001

Data Index: 803839 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2105. Min Act: -0.0001

Data Index: 437942 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1221262 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1877. Min Act: -0.0001

Data Index: 364677 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1115917 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1844. Min Act: -0.0001

Data Index: 706402 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2029. Min Act: -0.0001

Data Index: 1011514 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1895. Min Act: -0.0001

Data Index: 259482 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1873. Min Act: -0.0000

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1932. Min Act: -0.0001

Data Index: 721124 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2001. Min Act: -0.0000

Data Index: 573905 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1965. Min Act: -0.0001

Data Index: 376162 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1143611 (C4 (Web Text))

Max Activating Token Index: 153