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

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

Neuron 2430 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1220. Min Act: -0.0002

Data Index: 981452 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1325. Min Act: -0.0002

Data Index: 118793 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1240. Min Act: -0.0002

Data Index: 513367 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1330. Min Act: -0.0002

Data Index: 1340237 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0745. Min Act: -0.0002

Data Index: 358042 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1256517 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0889. Min Act: -0.0002

Data Index: 944590 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1048635 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0772. Min Act: -0.0002

Data Index: 464731 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0812. Min Act: -0.0002

Data Index: 944787 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0989. Min Act: -0.0002

Data Index: 676341 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1021725 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1339505 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0509. Min Act: -0.0002

Data Index: 474996 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1072. Min Act: -0.0002

Data Index: 518039 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0766. Min Act: -0.0002

Data Index: 778181 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0849. Min Act: -0.0002

Data Index: 418377 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1192210 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0766. Min Act: -0.0002

Data Index: 968397 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1214684 (C4 (Web Text))

Max Activating Token Index: 212