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

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

Neuron 4618 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: 2.7805. Min Range: -2.7805

Max Act: 2.7623. Min Act: -0.0000

Data Index: 730834 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.7805. Min Act: -0.0000

Data Index: 239008 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.6355. Min Act: -0.0000

Data Index: 884493 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.5763. Min Act: -0.0000

Data Index: 889480 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.6227. Min Act: -0.0000

Data Index: 449926 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.6258. Min Act: -0.0000

Data Index: 1079271 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.3933. Min Act: -0.0000

Data Index: 1260919 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.2735. Min Act: -0.0000

Data Index: 1330725 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.2519. Min Act: -0.0000

Data Index: 1058596 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.3603. Min Act: -0.0000

Data Index: 117196 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.4327. Min Act: -0.0000

Data Index: 13034 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.2556. Min Act: -0.0000

Data Index: 117754 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.2086. Min Act: -0.0000

Data Index: 251601 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.1851. Min Act: -0.0000

Data Index: 1351728 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 2.7805. Min Range: -2.7805

Max Act: 1.9220. Min Act: -0.0000

Data Index: 762454 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.1014. Min Act: -0.0000

Data Index: 732205 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.0990. Min Act: -0.0000

Data Index: 513794 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.1087. Min Act: -0.0000

Data Index: 973709 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.0435. Min Act: -0.0000

Data Index: 604955 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 2.7805. Min Range: -2.7805

Max Act: 2.2135. Min Act: -0.0000

Data Index: 1275714 (C4 (Web Text))

Max Activating Token Index: 885