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

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

Neuron 2392 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: 0.1140. Min Range: -0.1140

Max Act: 0.1129. Min Act: -0.0002

Data Index: 693224 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1140. Min Act: -0.0002

Data Index: 1211572 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1100. Min Act: -0.0002

Data Index: 225503 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1071. Min Act: -0.0002

Data Index: 283045 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1074. Min Act: -0.0002

Data Index: 922810 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1077. Min Act: -0.0002

Data Index: 859852 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1038. Min Act: -0.0002

Data Index: 549888 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1058. Min Act: -0.0002

Data Index: 20777 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1039. Min Act: -0.0002

Data Index: 514820 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1062. Min Act: -0.0002

Data Index: 702445 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1041. Min Act: -0.0002

Data Index: 381290 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1124543 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1014. Min Act: -0.0002

Data Index: 871978 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1014. Min Act: -0.0002

Data Index: 411914 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1028. Min Act: -0.0002

Data Index: 743769 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0994. Min Act: -0.0002

Data Index: 16576 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1010. Min Act: -0.0002

Data Index: 258104 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1001. Min Act: -0.0002

Data Index: 591078 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1015. Min Act: -0.0002

Data Index: 535427 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0999. Min Act: -0.0002

Data Index: 458878 (C4 (Web Text))

Max Activating Token Index: 695