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

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

Neuron 3239 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: 0.1439. Min Range: -0.1439

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1361275 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1503737 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1615948 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1495723 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1404990 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1474178 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1409568 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1544472 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1558223 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1457965 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1546677 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1624137 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1560528 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1487932 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1568145 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1491791 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1539434 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1375764 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1599906 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1467841 (Python Code)

Max Activating Token Index: 4