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

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

Neuron 4438 in Layer 0

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: 0.1090. Min Range: -0.1090

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1569254 (Python Code)

Max Activating Token Index: 356

Text #1

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1542539 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1403860 (Python Code)

Max Activating Token Index: 296

Text #3

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1599866 (Python Code)

Max Activating Token Index: 826

Text #4

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1483744 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1577419 (Python Code)

Max Activating Token Index: 277

Text #6

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1567905 (Python Code)

Max Activating Token Index: 209

Text #7

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1565075 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1505567 (Python Code)

Max Activating Token Index: 837

Text #9

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1409024 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1646809 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1545881 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1466353 (Python Code)

Max Activating Token Index: 527

Text #13

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1479506 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1475836 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1624280 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1363480 (Python Code)

Max Activating Token Index: 534

Text #17

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1417884 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1656988 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1627453 (Python Code)

Max Activating Token Index: 80