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

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

Neuron 477 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1251. Min Act: -0.0003

Data Index: 787743 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1091. Min Act: -0.0003

Data Index: 328428 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1028. Min Act: -0.0003

Data Index: 1244639 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1084. Min Act: -0.0003

Data Index: 1016637 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1028. Min Act: -0.0003

Data Index: 56372 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1007. Min Act: -0.0003

Data Index: 266944 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0935. Min Act: -0.0003

Data Index: 208747 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0964. Min Act: -0.0003

Data Index: 1152187 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0926. Min Act: -0.0003

Data Index: 883543 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0961. Min Act: -0.0003

Data Index: 629817 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0947. Min Act: -0.0003

Data Index: 1072905 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0915. Min Act: -0.0003

Data Index: 1332742 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0918. Min Act: -0.0003

Data Index: 383200 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1003. Min Act: -0.0003

Data Index: 525054 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0963. Min Act: -0.0003

Data Index: 835717 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1232054 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0922. Min Act: -0.0003

Data Index: 10854 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0922. Min Act: -0.0003

Data Index: 1276623 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0883. Min Act: -0.0003

Data Index: 868395 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0877. Min Act: -0.0003

Data Index: 30888 (C4 (Web Text))

Max Activating Token Index: 961