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

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

Neuron 298 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.3620. Min Act: -0.0000

Data Index: 741031 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.4220. Min Act: -0.0000

Data Index: 405044 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.4169. Min Act: -0.0000

Data Index: 700810 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1282684 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.3248. Min Act: -0.0000

Data Index: 557849 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.3491. Min Act: -0.0000

Data Index: 430131 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.2024. Min Act: -0.0000

Data Index: 781664 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1289784 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.0380. Min Act: -0.0000

Data Index: 129912 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9720. Min Act: -0.0000

Data Index: 887253 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9395. Min Act: 0.0000

Data Index: 1351495 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1268377 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9954. Min Act: -0.0000

Data Index: 781697 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9568. Min Act: -0.0000

Data Index: 639776 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9476. Min Act: -0.0000

Data Index: 982275 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9136. Min Act: -0.0000

Data Index: 865813 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.8873. Min Act: -0.0000

Data Index: 151269 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9012. Min Act: 0.0000

Data Index: 743002 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.8486. Min Act: -0.0000

Data Index: 882614 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.8769. Min Act: -0.0000

Data Index: 839580 (C4 (Web Text))

Max Activating Token Index: 269