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

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

Neuron 4849 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: 1.4662. Min Range: -1.4662

Max Act: 1.2625. Min Act: -0.0000

Data Index: 920868 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.3269. Min Act: -0.0000

Data Index: 155781 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.3153. Min Act: -0.0000

Data Index: 666813 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.4662. Min Act: -0.0000

Data Index: 1284183 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2567. Min Act: -0.0000

Data Index: 902069 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.1126. Min Act: -0.0000

Data Index: 291846 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.0498. Min Act: -0.0000

Data Index: 174466 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.9737. Min Act: -0.0000

Data Index: 852754 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.9727. Min Act: -0.0000

Data Index: 247767 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1186239 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.9585. Min Act: -0.0000

Data Index: 838140 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.9521. Min Act: -0.0000

Data Index: 7657 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.9479. Min Act: -0.0000

Data Index: 831549 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.0013. Min Act: -0.0000

Data Index: 480729 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1237496 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.8976. Min Act: -0.0000

Data Index: 938685 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.8634. Min Act: -0.0000

Data Index: 627340 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1027375 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1087555 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.4662. Min Range: -1.4662

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1219498 (C4 (Web Text))

Max Activating Token Index: 679