Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3471 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1797. Min Range: -3.1797

Max Act: 3.1797. Min Act: -0.0000

Data Index: 761548 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 3.1797. Min Range: -3.1797

Max Act: 3.0171. Min Act: -0.0000

Data Index: 96601 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.8555. Min Act: -0.0000

Data Index: 1067589 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.8400. Min Act: -0.0000

Data Index: 962334 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.7805. Min Act: -0.0000

Data Index: 912133 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.8756. Min Act: -0.0000

Data Index: 1159563 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.7155. Min Act: -0.0000

Data Index: 971182 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.6870. Min Act: -0.0000

Data Index: 341116 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.7768. Min Act: -0.0000

Data Index: 1265133 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.6262. Min Act: -0.0000

Data Index: 1012825 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.5879. Min Act: -0.0000

Data Index: 159325 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.4817. Min Act: -0.0000

Data Index: 537691 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.4619. Min Act: -0.0000

Data Index: 252970 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.4553. Min Act: -0.0000

Data Index: 1054879 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.4334. Min Act: -0.0000

Data Index: 258055 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.5264. Min Act: -0.0000

Data Index: 58791 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.4015. Min Act: -0.0000

Data Index: 452897 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.3911. Min Act: -0.0000

Data Index: 592157 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.3906. Min Act: -0.0000

Data Index: 322867 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 3.1797. Min Range: -3.1797

Max Act: 2.3782. Min Act: -0.0000

Data Index: 933973 (C4 (Web Text))

Max Activating Token Index: 418