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

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

Neuron 3738 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.7238. Min Act: -0.0000

Data Index: 313031 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.7584. Min Act: -0.0000

Data Index: 158846 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1174326 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5668. Min Act: -0.0000

Data Index: 830232 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1084306 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5225. Min Act: -0.0000

Data Index: 340913 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1332111 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5832. Min Act: -0.0000

Data Index: 519761 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5256. Min Act: -0.0000

Data Index: 362621 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.4919. Min Act: -0.0000

Data Index: 490438 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5565. Min Act: -0.0000

Data Index: 905666 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.4132. Min Act: -0.0000

Data Index: 112480 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5453. Min Act: -0.0000

Data Index: 873850 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5778. Min Act: -0.0000

Data Index: 316873 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.4746. Min Act: -0.0000

Data Index: 265061 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5033. Min Act: -0.0000

Data Index: 559298 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5298. Min Act: -0.0000

Data Index: 591589 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.4833. Min Act: -0.0000

Data Index: 915974 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.4097. Min Act: -0.0000

Data Index: 194533 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.4042. Min Act: -0.0000

Data Index: 174744 (C4 (Web Text))

Max Activating Token Index: 348