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

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

Neuron 597 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1380412 (Python Code)

Max Activating Token Index: 438

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1175618 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1045408 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0965. Min Act: -0.0000

Data Index: 74683 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1507161 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1295333 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0828. Min Act: -0.0000

Data Index: 372748 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0744. Min Act: -0.0000

Data Index: 150824 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0763. Min Act: -0.0000

Data Index: 48937 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0756. Min Act: -0.0000

Data Index: 813356 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0659. Min Act: -0.0000

Data Index: 217920 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0694. Min Act: -0.0000

Data Index: 627325 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0701. Min Act: -0.0000

Data Index: 43860 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0652. Min Act: -0.0000

Data Index: 963899 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1315923 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1126516 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1533651 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0673. Min Act: -0.0000

Data Index: 1421034 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1144747 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0636. Min Act: -0.0000

Data Index: 428880 (C4 (Web Text))

Max Activating Token Index: 934