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

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

Neuron 795 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5071. Min Act: -0.0000

Data Index: 1273487 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5759. Min Act: -0.0000

Data Index: 1251278 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5679. Min Act: -0.0000

Data Index: 20556 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5628. Min Act: -0.0000

Data Index: 416953 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5576. Min Act: -0.0000

Data Index: 800339 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5514. Min Act: -0.0000

Data Index: 456151 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.4667. Min Act: -0.0000

Data Index: 223174 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5311. Min Act: -0.0000

Data Index: 945544 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5340. Min Act: -0.0000

Data Index: 216585 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5334. Min Act: -0.0000

Data Index: 716187 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5294. Min Act: -0.0000

Data Index: 631042 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.4211. Min Act: -0.0000

Data Index: 1224998 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5058. Min Act: -0.0000

Data Index: 889462 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5056. Min Act: -0.0000

Data Index: 775645 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5011. Min Act: -0.0000

Data Index: 990635 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5035. Min Act: -0.0000

Data Index: 1015592 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5826. Min Act: -0.0000

Data Index: 235623 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.4045. Min Act: -0.0000

Data Index: 650210 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5803. Min Act: -0.0000

Data Index: 663424 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 1.5826. Min Range: -1.5826

Max Act: 1.5744. Min Act: -0.0000

Data Index: 405000 (C4 (Web Text))

Max Activating Token Index: 366