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

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

Neuron 2522 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1143505 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1346602 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1087647 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1228265 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0726. Min Act: -0.0000

Data Index: 527629 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1246711 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0001

Data Index: 930681 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0850. Min Act: -0.0001

Data Index: 123189 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1323198 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1183087 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0845. Min Act: -0.0001

Data Index: 989813 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0757. Min Act: -0.0000

Data Index: 170514 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0764. Min Act: -0.0000

Data Index: 436447 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0817. Min Act: -0.0000

Data Index: 200100 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0792. Min Act: -0.0001

Data Index: 419715 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1383069 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0769. Min Act: -0.0001

Data Index: 79826 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1244071 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1225703 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0709. Min Act: -0.0001

Data Index: 76572 (C4 (Web Text))

Max Activating Token Index: 517