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

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

Neuron 4923 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: 0.0102. Min Range: -0.0102

Max Act: 0.0100. Min Act: -0.0001

Data Index: 32713 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0001

Data Index: 722529 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0098. Min Act: -0.0001

Data Index: 1138080 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0098. Min Act: -0.0001

Data Index: 315568 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0099. Min Act: -0.0001

Data Index: 1261304 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0001

Data Index: 729150 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0001

Data Index: 29839 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0001

Data Index: 1227908 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0001

Data Index: 773651 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0001

Data Index: 876757 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0001

Data Index: 676897 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0001

Data Index: 1122130 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0001

Data Index: 887226 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0001

Data Index: 825101 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0001

Data Index: 137947 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0001

Data Index: 1237299 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0001

Data Index: 174137 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0001

Data Index: 50412 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0001

Data Index: 380977 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0001

Data Index: 1330436 (C4 (Web Text))

Max Activating Token Index: 427