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

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

Neuron 1362 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: 4.8744. Min Range: -4.8744

Max Act: 4.8744. Min Act: -0.0001

Data Index: 70115 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 4.8744. Min Range: -4.8744

Max Act: 4.4364. Min Act: -0.0001

Data Index: 68680 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 4.8744. Min Range: -4.8744

Max Act: 4.2233. Min Act: -0.0000

Data Index: 1294427 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 4.8744. Min Range: -4.8744

Max Act: 4.1870. Min Act: -0.0001

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 4.8744. Min Range: -4.8744

Max Act: 4.0028. Min Act: -0.0001

Data Index: 812808 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 4.8744. Min Range: -4.8744

Max Act: 4.0643. Min Act: -0.0000

Data Index: 495051 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 4.8744. Min Range: -4.8744

Max Act: 3.6492. Min Act: -0.0000

Data Index: 251079 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 4.8744. Min Range: -4.8744

Max Act: 4.3063. Min Act: -0.0001

Data Index: 409699 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 4.8744. Min Range: -4.8744

Max Act: 4.0056. Min Act: -0.0000

Data Index: 725318 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 4.8744. Min Range: -4.8744

Max Act: 3.9176. Min Act: -0.0001

Data Index: 1131215 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 4.8744. Min Range: -4.8744

Max Act: 3.7062. Min Act: -0.0001

Data Index: 924363 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 4.8744. Min Range: -4.8744

Max Act: 3.5733. Min Act: -0.0001

Data Index: 731698 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 4.8744. Min Range: -4.8744

Max Act: 3.4508. Min Act: -0.0001

Data Index: 250374 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 4.8744. Min Range: -4.8744

Max Act: 3.5440. Min Act: -0.0000

Data Index: 28974 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 4.8744. Min Range: -4.8744

Max Act: 2.7191. Min Act: -0.0000

Data Index: 745160 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 4.8744. Min Range: -4.8744

Max Act: 3.0704. Min Act: -0.0001

Data Index: 860772 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 4.8744. Min Range: -4.8744

Max Act: 2.9565. Min Act: -0.0000

Data Index: 1323721 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 4.8744. Min Range: -4.8744

Max Act: 2.9377. Min Act: -0.0001

Data Index: 1332272 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 4.8744. Min Range: -4.8744

Max Act: 2.8935. Min Act: -0.0000

Data Index: 1196702 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 4.8744. Min Range: -4.8744

Max Act: 2.8992. Min Act: -0.0000

Data Index: 298475 (C4 (Web Text))

Max Activating Token Index: 108