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

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

Neuron 1025 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1475086 (Python Code)

Max Activating Token Index: 533

Text #1

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.1014. Min Act: -0.0000

Data Index: 357544 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.1036. Min Act: -0.0000

Data Index: 742370 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0992. Min Act: -0.0000

Data Index: 403474 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0947. Min Act: -0.0000

Data Index: 596183 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1624451 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0996. Min Act: -0.0000

Data Index: 575790 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0837. Min Act: -0.0000

Data Index: 750338 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0878. Min Act: -0.0000

Data Index: 192514 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0911. Min Act: -0.0000

Data Index: 682683 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1303343 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0939. Min Act: -0.0000

Data Index: 442088 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1405339 (Python Code)

Max Activating Token Index: 63

Text #13

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0953. Min Act: -0.0000

Data Index: 611745 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0903. Min Act: -0.0000

Data Index: 739513 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0848. Min Act: -0.0000

Data Index: 330160 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0873. Min Act: -0.0000

Data Index: 250176 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1563751 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0890. Min Act: -0.0000

Data Index: 869730 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1383491 (Python Code)

Max Activating Token Index: 211