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

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

Neuron 3558 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1374. Min Act: -0.0002

Data Index: 1514445 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1253. Min Act: -0.0002

Data Index: 1493280 (Python Code)

Max Activating Token Index: 692

Text #2

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1282. Min Act: -0.0002

Data Index: 1443875 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1606038 (Python Code)

Max Activating Token Index: 884

Text #4

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1177. Min Act: -0.0002

Data Index: 1581671 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1369927 (Python Code)

Max Activating Token Index: 235

Text #6

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1492014 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1157. Min Act: -0.0002

Data Index: 1570240 (Python Code)

Max Activating Token Index: 499

Text #8

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1546094 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1178. Min Act: -0.0002

Data Index: 1560766 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1639518 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1447417 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1471630 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1107. Min Act: -0.0002

Data Index: 1505111 (Python Code)

Max Activating Token Index: 534

Text #14

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1550782 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1446994 (Python Code)

Max Activating Token Index: 134

Text #16

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1417430 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1496714 (Python Code)

Max Activating Token Index: 111

Text #18

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1627425 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1441984 (Python Code)

Max Activating Token Index: 384