Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1930 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.7901. Min Act: -0.0001

Data Index: 563865 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.7527. Min Act: -0.0001

Data Index: 368424 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.7470. Min Act: -0.0001

Data Index: 972756 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.7193. Min Act: -0.0001

Data Index: 550218 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6942. Min Act: -0.0001

Data Index: 862519 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6429. Min Act: -0.0001

Data Index: 1058260 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6332. Min Act: -0.0001

Data Index: 294413 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6471. Min Act: -0.0001

Data Index: 604629 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6200. Min Act: -0.0001

Data Index: 760533 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6215. Min Act: -0.0001

Data Index: 895473 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6454. Min Act: -0.0001

Data Index: 903549 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.5774. Min Act: -0.0001

Data Index: 174523 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6158. Min Act: -0.0001

Data Index: 321933 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6070. Min Act: -0.0001

Data Index: 83122 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.5870. Min Act: -0.0001

Data Index: 690627 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6102. Min Act: -0.0001

Data Index: 1274767 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6106. Min Act: -0.0001

Data Index: 1069790 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.5568. Min Act: -0.0001

Data Index: 1034498 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6112. Min Act: -0.0001

Data Index: 281462 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.7901. Min Range: -0.7901

Max Act: 0.6050. Min Act: -0.0001

Data Index: 906495 (C4 (Web Text))

Max Activating Token Index: 867