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

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

Neuron 1752 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2827. Min Range: -1.2827

Max Act: 1.2029. Min Act: 0.0000

Data Index: 946638 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.2827. Min Range: -1.2827

Max Act: 1.2827. Min Act: -0.0000

Data Index: 413742 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 1.2827. Min Range: -1.2827

Max Act: 1.0322. Min Act: -0.0000

Data Index: 345454 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.2827. Min Range: -1.2827

Max Act: 1.0435. Min Act: -0.0000

Data Index: 654669 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9457. Min Act: -0.0000

Data Index: 718180 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 1.2827. Min Range: -1.2827

Max Act: 1.0113. Min Act: -0.0000

Data Index: 597644 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9753. Min Act: -0.0000

Data Index: 331389 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1304278 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9149. Min Act: -0.0000

Data Index: 731432 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9344. Min Act: -0.0000

Data Index: 700088 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9766. Min Act: 0.0000

Data Index: 1357288 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9140. Min Act: -0.0000

Data Index: 343518 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1251881 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9197. Min Act: -0.0000

Data Index: 228756 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1067147 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9049. Min Act: -0.0000

Data Index: 801181 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1099544 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.6738. Min Act: -0.0000

Data Index: 941324 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7934. Min Act: -0.0000

Data Index: 821880 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.8351. Min Act: -0.0000

Data Index: 597714 (C4 (Web Text))

Max Activating Token Index: 971