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

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

Neuron 4408 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: 0.1174. Min Range: -0.1174

Max Act: 0.1174. Min Act: -0.0002

Data Index: 609778 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1147. Min Act: -0.0002

Data Index: 443860 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1124. Min Act: -0.0002

Data Index: 350396 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1096. Min Act: -0.0002

Data Index: 179426 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1107. Min Act: -0.0002

Data Index: 1200086 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1111. Min Act: -0.0002

Data Index: 604695 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1103. Min Act: -0.0002

Data Index: 924202 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1071. Min Act: -0.0003

Data Index: 1267668 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1211349 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1069. Min Act: -0.0002

Data Index: 39860 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1291471 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1092. Min Act: -0.0002

Data Index: 624115 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1087. Min Act: -0.0003

Data Index: 1004535 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1057. Min Act: -0.0002

Data Index: 25644 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1068. Min Act: -0.0002

Data Index: 725317 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1077. Min Act: -0.0002

Data Index: 918522 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1237696 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1059. Min Act: -0.0002

Data Index: 104874 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1065. Min Act: -0.0002

Data Index: 186292 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1035. Min Act: -0.0002

Data Index: 188095 (C4 (Web Text))

Max Activating Token Index: 19