Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 582 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.9170. Min Act: -0.0003

Data Index: 803351 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.9357. Min Act: -0.0003

Data Index: 867741 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.9399. Min Act: -0.0003

Data Index: 1224622 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8721. Min Act: -0.0003

Data Index: 618114 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8753. Min Act: -0.0003

Data Index: 862273 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8965. Min Act: -0.0003

Data Index: 627709 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8726. Min Act: -0.0003

Data Index: 626154 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.9828. Min Act: -0.0003

Data Index: 973825 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.7892. Min Act: -0.0003

Data Index: 226876 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8836. Min Act: -0.0003

Data Index: 899007 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8877. Min Act: -0.0003

Data Index: 459318 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8560. Min Act: -0.0003

Data Index: 902613 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.9214. Min Act: -0.0003

Data Index: 33011 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.9048. Min Act: -0.0003

Data Index: 291903 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8752. Min Act: -0.0003

Data Index: 1319659 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8816. Min Act: -0.0003

Data Index: 1106045 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.7860. Min Act: -0.0003

Data Index: 650189 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8454. Min Act: -0.0003

Data Index: 1212055 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.9163. Min Act: -0.0003

Data Index: 56608 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.9828. Min Range: -0.9828

Max Act: 0.8180. Min Act: -0.0003

Data Index: 1115950 (C4 (Web Text))

Max Activating Token Index: 534