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

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

Neuron 660 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.3857. Min Act: -0.0000

Data Index: 969531 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.2596. Min Act: -0.0000

Data Index: 422908 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1319149 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.2103. Min Act: -0.0000

Data Index: 84789 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.2050. Min Act: -0.0000

Data Index: 710135 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.2019. Min Act: -0.0000

Data Index: 1057530 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1834. Min Act: -0.0000

Data Index: 620442 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1238667 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1766. Min Act: -0.0000

Data Index: 680258 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0393. Min Act: -0.0000

Data Index: 318777 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0907. Min Act: -0.0000

Data Index: 30391 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1627. Min Act: -0.0000

Data Index: 207769 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0870. Min Act: -0.0000

Data Index: 84213 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0926. Min Act: -0.0000

Data Index: 641789 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0762. Min Act: -0.0000

Data Index: 200983 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0759. Min Act: -0.0000

Data Index: 44580 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0623. Min Act: -0.0000

Data Index: 315846 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0425. Min Act: -0.0000

Data Index: 395085 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9769. Min Act: -0.0000

Data Index: 765144 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0479. Min Act: -0.0000

Data Index: 744676 (C4 (Web Text))

Max Activating Token Index: 284