Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4704 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1043682 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1055091 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5135. Min Act: -0.0000

Data Index: 859766 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5348. Min Act: -0.0000

Data Index: 426033 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5840. Min Act: -0.0000

Data Index: 424589 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1239879 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5045. Min Act: 0.0000

Data Index: 358884 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4859. Min Act: -0.0000

Data Index: 832425 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4879. Min Act: -0.0000

Data Index: 42620 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4377. Min Act: -0.0000

Data Index: 164926 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4299. Min Act: -0.0000

Data Index: 813055 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4889. Min Act: -0.0000

Data Index: 645570 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4299. Min Act: -0.0000

Data Index: 108008 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4135. Min Act: -0.0000

Data Index: 624835 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3436. Min Act: -0.0000

Data Index: 186319 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3601. Min Act: -0.0000

Data Index: 636110 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4281. Min Act: -0.0000

Data Index: 514924 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4102. Min Act: -0.0000

Data Index: 616889 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1283034 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3885. Min Act: -0.0000

Data Index: 518402 (C4 (Web Text))

Max Activating Token Index: 723