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

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

Neuron 1425 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1063007 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2432. Min Act: -0.0001

Data Index: 58367 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2269. Min Act: -0.0001

Data Index: 758559 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2311. Min Act: -0.0001

Data Index: 573334 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2131. Min Act: -0.0001

Data Index: 39801 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2110. Min Act: -0.0001

Data Index: 574616 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2215. Min Act: -0.0001

Data Index: 415628 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2165. Min Act: -0.0001

Data Index: 34334 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2150. Min Act: -0.0001

Data Index: 116950 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2071. Min Act: -0.0001

Data Index: 347924 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.1931. Min Act: -0.0001

Data Index: 67762 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2015. Min Act: -0.0001

Data Index: 40481 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.1979. Min Act: -0.0001

Data Index: 306181 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2074. Min Act: -0.0001

Data Index: 699734 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.1905. Min Act: -0.0001

Data Index: 423544 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.1883. Min Act: -0.0001

Data Index: 120910 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.1955. Min Act: -0.0001

Data Index: 498773 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1041735 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.1899. Min Act: -0.0001

Data Index: 443479 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.1928. Min Act: -0.0001

Data Index: 757705 (C4 (Web Text))

Max Activating Token Index: 431