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

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

Neuron 4116 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2587. Min Range: -1.2587

Max Act: 1.2587. Min Act: -0.0000

Data Index: 437146 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.2587. Min Range: -1.2587

Max Act: 1.1555. Min Act: -0.0000

Data Index: 408836 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.2587. Min Range: -1.2587

Max Act: 1.2009. Min Act: -0.0000

Data Index: 524913 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9751. Min Act: -0.0000

Data Index: 876941 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 1.2587. Min Range: -1.2587

Max Act: 1.0024. Min Act: -0.0000

Data Index: 393389 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1146757 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9744. Min Act: -0.0000

Data Index: 713597 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9360. Min Act: -0.0000

Data Index: 741914 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8746. Min Act: -0.0000

Data Index: 595060 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8673. Min Act: -0.0000

Data Index: 91613 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1024047 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9026. Min Act: -0.0000

Data Index: 549353 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1213757 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9312. Min Act: -0.0000

Data Index: 696574 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1247574 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8649. Min Act: -0.0000

Data Index: 686431 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8277. Min Act: -0.0000

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9324. Min Act: -0.0000

Data Index: 998029 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8383. Min Act: -0.0000

Data Index: 347182 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8467. Min Act: -0.0000

Data Index: 285629 (C4 (Web Text))

Max Activating Token Index: 473