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

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

Neuron 815 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: 0.0694. Min Range: -0.0694

Max Act: 0.0694. Min Act: -0.0002

Data Index: 896778 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0579. Min Act: -0.0002

Data Index: 637521 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0582. Min Act: -0.0002

Data Index: 457344 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1119149 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0511. Min Act: -0.0002

Data Index: 513370 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0516. Min Act: -0.0002

Data Index: 962537 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1655821 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1465559 (Python Code)

Max Activating Token Index: 581

Text #8

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1546904 (Python Code)

Max Activating Token Index: 402

Text #9

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0439. Min Act: -0.0002

Data Index: 519655 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0438. Min Act: -0.0002

Data Index: 479863 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1267730 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0433. Min Act: -0.0003

Data Index: 489734 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1604298 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1169306 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0414. Min Act: -0.0002

Data Index: 391242 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1455216 (Python Code)

Max Activating Token Index: 465

Text #17

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1403049 (Python Code)

Max Activating Token Index: 765

Text #18

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0402. Min Act: -0.0002

Data Index: 139744 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1218682 (C4 (Web Text))

Max Activating Token Index: 113