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

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

Neuron 3338 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5698. Min Act: -0.0000

Data Index: 118551 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.3864. Min Act: -0.0000

Data Index: 1255064 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1036935 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4650. Min Act: -0.0000

Data Index: 1019881 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.3609. Min Act: -0.0000

Data Index: 852784 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5128. Min Act: -0.0000

Data Index: 1139941 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.3237. Min Act: -0.0000

Data Index: 376377 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.3926. Min Act: -0.0000

Data Index: 780915 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.3143. Min Act: -0.0000

Data Index: 177575 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4631. Min Act: -0.0000

Data Index: 526169 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4600. Min Act: -0.0000

Data Index: 421561 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.2850. Min Act: -0.0000

Data Index: 205622 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4559. Min Act: -0.0000

Data Index: 419680 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.2803. Min Act: -0.0000

Data Index: 557721 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.2433. Min Act: -0.0000

Data Index: 318812 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4010. Min Act: -0.0000

Data Index: 484803 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.3941. Min Act: -0.0000

Data Index: 971376 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.2715. Min Act: -0.0000

Data Index: 477311 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.3136. Min Act: -0.0000

Data Index: 213639 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.3076. Min Act: -0.0000

Data Index: 402481 (C4 (Web Text))

Max Activating Token Index: 669