Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2333 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1391893 (Python Code)

Max Activating Token Index: 794

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1617567 (Python Code)

Max Activating Token Index: 742

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1388952 (Python Code)

Max Activating Token Index: 700

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1488974 (Python Code)

Max Activating Token Index: 845

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1438602 (Python Code)

Max Activating Token Index: 669

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1557873 (Python Code)

Max Activating Token Index: 700

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1511955 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1560101 (Python Code)

Max Activating Token Index: 643

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1584214 (Python Code)

Max Activating Token Index: 892

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1464674 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1634026 (Python Code)

Max Activating Token Index: 850

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1508306 (Python Code)

Max Activating Token Index: 785

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1130276 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1655674 (Python Code)

Max Activating Token Index: 787

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1558758 (Python Code)

Max Activating Token Index: 797

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1636230 (Python Code)

Max Activating Token Index: 749

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1584032 (Python Code)

Max Activating Token Index: 749

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1654463 (Python Code)

Max Activating Token Index: 777

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0139. Min Act: -0.0003

Data Index: 424350 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1466363 (Python Code)

Max Activating Token Index: 722