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

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

Neuron 5707 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: 0.0058. Min Range: -0.0058

Max Act: 0.0058. Min Act: -0.0001

Data Index: 1064379 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0054. Min Act: -0.0001

Data Index: 1589586 (Python Code)

Max Activating Token Index: 809

Text #2

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1591592 (Python Code)

Max Activating Token Index: 871

Text #3

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1620490 (Python Code)

Max Activating Token Index: 873

Text #4

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0051. Min Act: -0.0001

Data Index: 1614792 (Python Code)

Max Activating Token Index: 886

Text #5

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0050. Min Act: -0.0001

Data Index: 1550098 (Python Code)

Max Activating Token Index: 725

Text #6

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0049. Min Act: -0.0001

Data Index: 808297 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0049. Min Act: -0.0001

Data Index: 1597287 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0002

Data Index: 998018 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0001

Data Index: 1391989 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0001

Data Index: 1607583 (Python Code)

Max Activating Token Index: 849

Text #11

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0001

Data Index: 10833 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0001

Data Index: 63485 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0047. Min Act: -0.0001

Data Index: 1584371 (Python Code)

Max Activating Token Index: 750

Text #14

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0046. Min Act: -0.0001

Data Index: 374222 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0046. Min Act: -0.0001

Data Index: 1387022 (Python Code)

Max Activating Token Index: 800

Text #16

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0047. Min Act: -0.0001

Data Index: 1429326 (Python Code)

Max Activating Token Index: 830

Text #17

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0046. Min Act: -0.0001

Data Index: 1434936 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0046. Min Act: -0.0001

Data Index: 1225389 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0045. Min Act: -0.0001

Data Index: 461521 (C4 (Web Text))

Max Activating Token Index: 854