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

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

Neuron 2096 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.8540. Min Act: -0.0000

Data Index: 1107727 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.6128. Min Act: -0.0000

Data Index: 630371 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.6497. Min Act: -0.0000

Data Index: 1051714 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.1971. Min Act: -0.0000

Data Index: 94712 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.1744. Min Act: -0.0000

Data Index: 235370 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.1773. Min Act: -0.0000

Data Index: 469617 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.1840. Min Act: -0.0000

Data Index: 399013 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.2952. Min Act: -0.0000

Data Index: 79375 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.4715. Min Act: -0.0000

Data Index: 867619 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.2680. Min Act: -0.0000

Data Index: 999904 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.2569. Min Act: -0.0000

Data Index: 934683 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.0415. Min Act: -0.0000

Data Index: 1273640 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.5150. Min Act: -0.0000

Data Index: 274883 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.1494. Min Act: -0.0000

Data Index: 344861 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.3159. Min Act: -0.0000

Data Index: 1017769 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.3068. Min Act: -0.0000

Data Index: 953237 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 4.8540. Min Range: -4.8540

Max Act: 3.9516. Min Act: -0.0000

Data Index: 995833 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 4.8540. Min Range: -4.8540

Max Act: 3.9635. Min Act: -0.0000

Data Index: 1004988 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.0887. Min Act: -0.0000

Data Index: 1069683 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 4.8540. Min Range: -4.8540

Max Act: 4.0881. Min Act: -0.0000

Data Index: 1230984 (C4 (Web Text))

Max Activating Token Index: 271