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

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

Neuron 605 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.3305. Min Act: -0.0000

Data Index: 459633 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.2294. Min Act: -0.0000

Data Index: 8747 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.2930. Min Act: -0.0000

Data Index: 107229 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1604. Min Act: -0.0000

Data Index: 569192 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1356. Min Act: -0.0000

Data Index: 633564 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0934. Min Act: -0.0000

Data Index: 66608 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0855. Min Act: -0.0000

Data Index: 402940 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0785. Min Act: -0.0000

Data Index: 470100 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1803. Min Act: -0.0000

Data Index: 33235 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1255101 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0836. Min Act: -0.0000

Data Index: 1153895 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9505. Min Act: -0.0000

Data Index: 592191 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0442. Min Act: -0.0000

Data Index: 955286 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1273517 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9884. Min Act: -0.0000

Data Index: 109204 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0481. Min Act: -0.0000

Data Index: 462490 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0440. Min Act: -0.0000

Data Index: 777445 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0298. Min Act: -0.0000

Data Index: 880256 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0850. Min Act: -0.0000

Data Index: 141319 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9826. Min Act: -0.0000

Data Index: 398607 (C4 (Web Text))

Max Activating Token Index: 744