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

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

Neuron 845 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.4836. Min Act: -0.0001

Data Index: 261927 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.8771. Min Act: -0.0001

Data Index: 497736 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.8771. Min Act: -0.0001

Data Index: 1193408 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.8836. Min Act: -0.0001

Data Index: 1329747 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.3870. Min Act: -0.0001

Data Index: 920867 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.3423. Min Act: -0.0001

Data Index: 1343197 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.5660. Min Act: -0.0001

Data Index: 108223 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.3122. Min Act: -0.0001

Data Index: 443883 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.5597. Min Act: -0.0001

Data Index: 184964 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.1326. Min Act: -0.0001

Data Index: 677768 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 3.4836. Min Range: -3.4836

Max Act: 1.9926. Min Act: -0.0001

Data Index: 448383 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.0294. Min Act: -0.0001

Data Index: 1193594 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.2105. Min Act: -0.0001

Data Index: 1065687 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 3.4836. Min Range: -3.4836

Max Act: 2.1457. Min Act: -0.0001

Data Index: 1106975 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 3.4836. Min Range: -3.4836

Max Act: 1.8978. Min Act: -0.0001

Data Index: 291768 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 3.4836. Min Range: -3.4836

Max Act: 1.9952. Min Act: -0.0001

Data Index: 1336176 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 3.4836. Min Range: -3.4836

Max Act: 1.9890. Min Act: -0.0001

Data Index: 332307 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 3.4836. Min Range: -3.4836

Max Act: 1.8670. Min Act: -0.0001

Data Index: 1199687 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 3.4836. Min Range: -3.4836

Max Act: 1.8414. Min Act: -0.0001

Data Index: 1054332 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 3.4836. Min Range: -3.4836

Max Act: 1.9422. Min Act: -0.0001

Data Index: 539686 (C4 (Web Text))

Max Activating Token Index: 215