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

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

Neuron 2000 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2926. Min Act: -0.0000

Data Index: 208115 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1111845 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1073069 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1004505 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2025. Min Act: -0.0001

Data Index: 208724 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2195. Min Act: -0.0000

Data Index: 440002 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1101199 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2043. Min Act: -0.0000

Data Index: 569096 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2056. Min Act: -0.0000

Data Index: 5217 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1958. Min Act: -0.0000

Data Index: 659689 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1289589 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2126. Min Act: -0.0000

Data Index: 390469 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2017. Min Act: -0.0001

Data Index: 616454 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2015. Min Act: -0.0001

Data Index: 564925 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1036924 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1844. Min Act: -0.0000

Data Index: 664351 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1891. Min Act: -0.0001

Data Index: 697123 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1767. Min Act: -0.0001

Data Index: 436653 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1291065 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1652. Min Act: -0.0000

Data Index: 130379 (C4 (Web Text))

Max Activating Token Index: 234