Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 757 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0915. Min Act: -0.0003

Data Index: 391732 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0927. Min Act: -0.0003

Data Index: 772873 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0819. Min Act: -0.0003

Data Index: 51297 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0814. Min Act: -0.0003

Data Index: 671140 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0798. Min Act: -0.0003

Data Index: 749315 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0811. Min Act: -0.0002

Data Index: 696032 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0810. Min Act: -0.0003

Data Index: 642898 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0784. Min Act: -0.0003

Data Index: 1257397 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0754. Min Act: -0.0003

Data Index: 661252 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0741. Min Act: -0.0002

Data Index: 861734 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0763. Min Act: -0.0003

Data Index: 595943 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0747. Min Act: -0.0003

Data Index: 822877 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0764. Min Act: -0.0003

Data Index: 813003 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1014824 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0725. Min Act: -0.0003

Data Index: 66524 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0749. Min Act: -0.0003

Data Index: 383347 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0769. Min Act: -0.0003

Data Index: 892550 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0748. Min Act: -0.0003

Data Index: 100497 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0758. Min Act: -0.0003

Data Index: 666505 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0750. Min Act: -0.0003

Data Index: 438042 (C4 (Web Text))

Max Activating Token Index: 154