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

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

Neuron 4368 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1392. Min Act: -0.0001

Data Index: 596909 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1063. Min Act: -0.0001

Data Index: 931273 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0976. Min Act: -0.0002

Data Index: 736481 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1083611 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1232392 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0943. Min Act: -0.0001

Data Index: 659364 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0891. Min Act: -0.0001

Data Index: 943688 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0951. Min Act: -0.0001

Data Index: 66855 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0876. Min Act: -0.0001

Data Index: 517438 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1068015 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1112727 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0886. Min Act: -0.0001

Data Index: 884068 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1101980 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0797. Min Act: -0.0001

Data Index: 849870 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1248417 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0797. Min Act: -0.0002

Data Index: 617174 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0786. Min Act: -0.0001

Data Index: 118048 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0796. Min Act: -0.0001

Data Index: 238994 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0788. Min Act: -0.0001

Data Index: 811722 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0773. Min Act: -0.0001

Data Index: 632595 (C4 (Web Text))

Max Activating Token Index: 196