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

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

Neuron 3784 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: 0.1255. Min Range: -0.1255

Max Act: 0.1255. Min Act: -0.0002

Data Index: 639866 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1161. Min Act: -0.0003

Data Index: 870898 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1144. Min Act: -0.0002

Data Index: 4057 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1140922 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1133. Min Act: -0.0002

Data Index: 379890 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1149. Min Act: -0.0002

Data Index: 499415 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1255501 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1112. Min Act: -0.0002

Data Index: 398759 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1035554 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1112. Min Act: -0.0002

Data Index: 148701 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1097. Min Act: -0.0002

Data Index: 590687 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1103. Min Act: -0.0002

Data Index: 68140 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1105. Min Act: -0.0002

Data Index: 133852 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1092. Min Act: -0.0002

Data Index: 916619 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1088. Min Act: -0.0002

Data Index: 366921 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1067. Min Act: -0.0002

Data Index: 722061 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1102. Min Act: -0.0003

Data Index: 985077 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1061. Min Act: -0.0002

Data Index: 1240671 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1073. Min Act: -0.0002

Data Index: 868804 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1179710 (C4 (Web Text))

Max Activating Token Index: 756