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

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

Neuron 255 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0002

Data Index: 894964 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1470258 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1179975 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1437131 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0777. Min Act: -0.0002

Data Index: 662279 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1586257 (Python Code)

Max Activating Token Index: 313

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1486873 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1472642 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1096524 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1246769 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1380458 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0737. Min Act: -0.0002

Data Index: 519475 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0725. Min Act: -0.0002

Data Index: 3294 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1578951 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1646367 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1625563 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1416476 (Python Code)

Max Activating Token Index: 305

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0727. Min Act: -0.0002

Data Index: 30801 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1172693 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0729. Min Act: -0.0002

Data Index: 708434 (C4 (Web Text))

Max Activating Token Index: 157