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

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

Neuron 1221 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: 0.9552. Min Range: -0.9552

Max Act: 0.9552. Min Act: -0.0000

Data Index: 241671 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1189042 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6612. Min Act: -0.0000

Data Index: 459957 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6581. Min Act: -0.0000

Data Index: 678277 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1037970 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6271. Min Act: -0.0000

Data Index: 595714 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6226. Min Act: -0.0000

Data Index: 303139 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1642839 (Python Code)

Max Activating Token Index: 618

Text #8

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1085837 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6056. Min Act: -0.0000

Data Index: 372216 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6017. Min Act: -0.0000

Data Index: 283035 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6043. Min Act: -0.0000

Data Index: 204019 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1232020 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6172. Min Act: -0.0000

Data Index: 56055 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1186223 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.5891. Min Act: -0.0000

Data Index: 12400 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.5990. Min Act: -0.0000

Data Index: 929864 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.5600. Min Act: 0.0000

Data Index: 1135507 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.5591. Min Act: -0.0000

Data Index: 904915 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.5573. Min Act: -0.0000

Data Index: 755856 (C4 (Web Text))

Max Activating Token Index: 856