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

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

Neuron 989 in Layer 1

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: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1535827 (Python Code)

Max Activating Token Index: 809

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1533028 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1126. Min Act: -0.0002

Data Index: 1656486 (Python Code)

Max Activating Token Index: 776

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1580223 (Python Code)

Max Activating Token Index: 672

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1482632 (Python Code)

Max Activating Token Index: 651

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1395016 (Python Code)

Max Activating Token Index: 200

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1549458 (Python Code)

Max Activating Token Index: 951

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1474841 (Python Code)

Max Activating Token Index: 994

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1411372 (Python Code)

Max Activating Token Index: 683

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1615347 (Python Code)

Max Activating Token Index: 313

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1386568 (Python Code)

Max Activating Token Index: 562

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1389908 (Python Code)

Max Activating Token Index: 587

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1558425 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1380557 (Python Code)

Max Activating Token Index: 816

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1568893 (Python Code)

Max Activating Token Index: 744

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1362873 (Python Code)

Max Activating Token Index: 833

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1445810 (Python Code)

Max Activating Token Index: 237

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1446254 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1526109 (Python Code)

Max Activating Token Index: 521

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1382524 (Python Code)

Max Activating Token Index: 306