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

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

Neuron 1863 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5877. Min Act: -0.0000

Data Index: 495490 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1179603 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4923. Min Act: -0.0000

Data Index: 506384 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5021. Min Act: -0.0000

Data Index: 363269 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4727. Min Act: -0.0000

Data Index: 564725 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4698. Min Act: -0.0000

Data Index: 445704 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4179. Min Act: -0.0000

Data Index: 985835 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4325. Min Act: -0.0000

Data Index: 374460 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4077. Min Act: -0.0000

Data Index: 130254 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4109. Min Act: -0.0000

Data Index: 506209 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1232640 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4049. Min Act: -0.0000

Data Index: 835462 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.3735. Min Act: -0.0000

Data Index: 907825 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.3981. Min Act: -0.0000

Data Index: 365187 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1072950 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4024. Min Act: -0.0000

Data Index: 991490 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4157. Min Act: -0.0000

Data Index: 590347 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1287430 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4149. Min Act: -0.0000

Data Index: 168550 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.3825. Min Act: -0.0000

Data Index: 989339 (C4 (Web Text))

Max Activating Token Index: 182