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

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

Neuron 2692 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1160613 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0913. Min Act: -0.0000

Data Index: 572881 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1141066 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0889. Min Act: -0.0000

Data Index: 460351 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1338206 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0000

Data Index: 439984 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0901. Min Act: -0.0000

Data Index: 985822 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1010557 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0748. Min Act: -0.0000

Data Index: 122423 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0872. Min Act: -0.0000

Data Index: 780769 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0857. Min Act: -0.0000

Data Index: 465521 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0851. Min Act: -0.0000

Data Index: 396956 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0809. Min Act: -0.0000

Data Index: 534529 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0834. Min Act: -0.0000

Data Index: 49845 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0803. Min Act: -0.0000

Data Index: 564710 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0850. Min Act: -0.0000

Data Index: 889903 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0797. Min Act: -0.0000

Data Index: 444422 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0775. Min Act: -0.0000

Data Index: 558213 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0807. Min Act: -0.0000

Data Index: 881565 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0803. Min Act: -0.0000

Data Index: 659352 (C4 (Web Text))

Max Activating Token Index: 951