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

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

Neuron 5995 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0248. Min Act: -0.0001

Data Index: 38558 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0001

Data Index: 311326 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0222. Min Act: -0.0001

Data Index: 273167 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0208. Min Act: -0.0001

Data Index: 632634 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0206. Min Act: -0.0001

Data Index: 536994 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0177. Min Act: -0.0001

Data Index: 881438 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1252449 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0189. Min Act: -0.0001

Data Index: 1271633 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0180. Min Act: -0.0001

Data Index: 547789 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0184. Min Act: -0.0002

Data Index: 321203 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0182. Min Act: -0.0001

Data Index: 985666 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0144. Min Act: -0.0001

Data Index: 867836 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0151. Min Act: -0.0001

Data Index: 358166 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0108. Min Act: -0.0001

Data Index: 370516 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0153. Min Act: -0.0001

Data Index: 581048 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0175. Min Act: -0.0001

Data Index: 212769 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0162. Min Act: -0.0001

Data Index: 445282 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1620033 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0140. Min Act: -0.0001

Data Index: 287166 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1285430 (C4 (Web Text))

Max Activating Token Index: 634