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

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

Neuron 4590 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1627324 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1303. Min Act: -0.0002

Data Index: 1424478 (Python Code)

Max Activating Token Index: 842

Text #2

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1602921 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1249. Min Act: -0.0002

Data Index: 1521885 (Python Code)

Max Activating Token Index: 165

Text #4

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1210. Min Act: -0.0002

Data Index: 1539064 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1487976 (Python Code)

Max Activating Token Index: 817

Text #6

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1436625 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1412709 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1629909 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1641633 (Python Code)

Max Activating Token Index: 871

Text #10

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1450008 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1488276 (Python Code)

Max Activating Token Index: 1002

Text #12

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1647869 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1400753 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1116. Min Act: -0.0002

Data Index: 1620121 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1563482 (Python Code)

Max Activating Token Index: 968

Text #16

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1652343 (Python Code)

Max Activating Token Index: 811

Text #17

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1507264 (Python Code)

Max Activating Token Index: 374

Text #18

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1554835 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1525306 (Python Code)

Max Activating Token Index: 243