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

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

Neuron 282 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1330109 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5979. Min Act: -0.0000

Data Index: 590389 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5750. Min Act: -0.0000

Data Index: 984197 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5356. Min Act: -0.0000

Data Index: 653183 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5135. Min Act: -0.0000

Data Index: 59795 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4829. Min Act: 0.0000

Data Index: 1568920 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5039. Min Act: -0.0000

Data Index: 131399 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4526. Min Act: 0.0001

Data Index: 1131049 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4441. Min Act: 0.0000

Data Index: 498326 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1006817 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4153. Min Act: -0.0000

Data Index: 371577 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3808. Min Act: -0.0000

Data Index: 460827 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3987. Min Act: -0.0000

Data Index: 810628 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1008576 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3641. Min Act: -0.0000

Data Index: 704848 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3807. Min Act: -0.0000

Data Index: 6571 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3718. Min Act: -0.0000

Data Index: 171027 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3702. Min Act: -0.0000

Data Index: 728512 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1088674 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3572. Min Act: -0.0000

Data Index: 537184 (C4 (Web Text))

Max Activating Token Index: 853