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

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

Neuron 2994 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1754. Min Act: -0.0001

Data Index: 1073031 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1843. Min Act: -0.0001

Data Index: 93481 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1243. Min Act: -0.0001

Data Index: 752250 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.8693. Min Act: -0.0001

Data Index: 685708 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.8527. Min Act: -0.0001

Data Index: 1277261 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.8013. Min Act: -0.0001

Data Index: 1116938 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.6237. Min Act: -0.0001

Data Index: 879824 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.6107. Min Act: -0.0001

Data Index: 495690 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.7372. Min Act: -0.0001

Data Index: 561073 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.8647. Min Act: -0.0001

Data Index: 1111380 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.7010. Min Act: -0.0001

Data Index: 983773 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.7851. Min Act: -0.0001

Data Index: 1064324 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.6465. Min Act: -0.0001

Data Index: 192845 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.6174. Min Act: -0.0001

Data Index: 1228565 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.6165. Min Act: -0.0001

Data Index: 224687 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.4509. Min Act: -0.0001

Data Index: 934551 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.5692. Min Act: -0.0000

Data Index: 187270 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.5264. Min Act: -0.0001

Data Index: 1181699 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.5171. Min Act: -0.0000

Data Index: 709880 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.5102. Min Act: -0.0001

Data Index: 379031 (C4 (Web Text))

Max Activating Token Index: 297