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

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

Neuron 319 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2550. Min Act: -0.0001

Data Index: 1151076 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2565. Min Act: -0.0001

Data Index: 1235580 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2334. Min Act: -0.0001

Data Index: 1106683 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2223. Min Act: -0.0001

Data Index: 502693 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2123. Min Act: -0.0001

Data Index: 77936 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1077905 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2040. Min Act: -0.0000

Data Index: 931716 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1046218 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1999. Min Act: -0.0001

Data Index: 1497475 (Python Code)

Max Activating Token Index: 486

Text #9

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1991. Min Act: -0.0001

Data Index: 523983 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.2031. Min Act: -0.0001

Data Index: 638566 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1692. Min Act: -0.0001

Data Index: 75310 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1899. Min Act: -0.0001

Data Index: 337087 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1903. Min Act: -0.0001

Data Index: 432987 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1882. Min Act: -0.0001

Data Index: 373035 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1837. Min Act: -0.0001

Data Index: 908885 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1832. Min Act: -0.0001

Data Index: 444712 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1909. Min Act: -0.0001

Data Index: 537724 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1801. Min Act: -0.0001

Data Index: 319166 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.2565. Min Range: -0.2565

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1407512 (Python Code)

Max Activating Token Index: 540