Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1587 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3714. Min Act: -0.0001

Data Index: 683795 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3383. Min Act: -0.0001

Data Index: 1108907 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3222. Min Act: -0.0001

Data Index: 335706 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3276. Min Act: -0.0001

Data Index: 211832 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3007. Min Act: -0.0001

Data Index: 441498 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2875. Min Act: -0.0001

Data Index: 784753 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3128. Min Act: -0.0001

Data Index: 1189903 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2894. Min Act: -0.0001

Data Index: 657873 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3141. Min Act: -0.0001

Data Index: 997418 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3024. Min Act: -0.0001

Data Index: 145659 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3032. Min Act: -0.0001

Data Index: 510947 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2964. Min Act: -0.0001

Data Index: 126607 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2852. Min Act: -0.0001

Data Index: 1106417 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2929. Min Act: -0.0001

Data Index: 748976 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.3073. Min Act: -0.0001

Data Index: 557002 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2817. Min Act: -0.0001

Data Index: 780056 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2651. Min Act: -0.0001

Data Index: 436240 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2766. Min Act: -0.0001

Data Index: 1222593 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2719. Min Act: -0.0001

Data Index: 237684 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.3714. Min Range: -0.3714

Max Act: 0.2618. Min Act: -0.0001

Data Index: 73320 (C4 (Web Text))

Max Activating Token Index: 12