Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1909 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1654. Min Act: -0.0003

Data Index: 1562245 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1410. Min Act: -0.0003

Data Index: 127055 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1334. Min Act: -0.0004

Data Index: 1501642 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1219. Min Act: -0.0003

Data Index: 232705 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1240. Min Act: -0.0003

Data Index: 1317340 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1331. Min Act: -0.0003

Data Index: 1360650 (Python Code)

Max Activating Token Index: 779

Text #6

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1294. Min Act: -0.0003

Data Index: 1531183 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1217. Min Act: -0.0003

Data Index: 1123544 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1242. Min Act: -0.0003

Data Index: 1379377 (Python Code)

Max Activating Token Index: 514

Text #9

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1186. Min Act: -0.0003

Data Index: 1506512 (Python Code)

Max Activating Token Index: 863

Text #10

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1162. Min Act: -0.0003

Data Index: 1656255 (Python Code)

Max Activating Token Index: 673

Text #11

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1135. Min Act: -0.0003

Data Index: 1611241 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1197. Min Act: -0.0003

Data Index: 1603841 (Python Code)

Max Activating Token Index: 783

Text #13

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1137. Min Act: -0.0003

Data Index: 1535516 (Python Code)

Max Activating Token Index: 882

Text #14

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1153. Min Act: -0.0003

Data Index: 1376237 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1139. Min Act: -0.0003

Data Index: 1549678 (Python Code)

Max Activating Token Index: 471

Text #16

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1513222 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1138. Min Act: -0.0003

Data Index: 1359998 (Python Code)

Max Activating Token Index: 531

Text #18

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1078. Min Act: -0.0003

Data Index: 1586027 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1056. Min Act: -0.0003

Data Index: 1606459 (Python Code)

Max Activating Token Index: 430