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

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

Neuron 5171 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: 2.7877. Min Range: -2.7877

Max Act: 2.7877. Min Act: -0.0000

Data Index: 815848 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.6307. Min Act: -0.0000

Data Index: 316798 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.2414. Min Act: -0.0000

Data Index: 996003 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.4886. Min Act: -0.0000

Data Index: 1083143 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.1783. Min Act: -0.0000

Data Index: 225311 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.1315. Min Act: -0.0000

Data Index: 251765 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.1913. Min Act: -0.0000

Data Index: 1069192 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.2694. Min Act: -0.0000

Data Index: 913185 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.1818. Min Act: -0.0000

Data Index: 716615 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 2.7877. Min Range: -2.7877

Max Act: 1.9867. Min Act: -0.0000

Data Index: 123252 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.1859. Min Act: -0.0000

Data Index: 463989 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.0765. Min Act: -0.0000

Data Index: 222245 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.1792. Min Act: -0.0000

Data Index: 828794 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 2.7877. Min Range: -2.7877

Max Act: 1.9384. Min Act: -0.0000

Data Index: 318863 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 2.7877. Min Range: -2.7877

Max Act: 1.9815. Min Act: -0.0000

Data Index: 850249 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.0010. Min Act: -0.0000

Data Index: 291004 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 2.7877. Min Range: -2.7877

Max Act: 1.9633. Min Act: -0.0000

Data Index: 1253409 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 2.7877. Min Range: -2.7877

Max Act: 1.9715. Min Act: -0.0000

Data Index: 228079 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 2.7877. Min Range: -2.7877

Max Act: 2.0622. Min Act: -0.0000

Data Index: 1205290 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 2.7877. Min Range: -2.7877

Max Act: 1.9504. Min Act: -0.0000

Data Index: 1106560 (C4 (Web Text))

Max Activating Token Index: 708