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

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

Neuron 624 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1166. Min Act: -0.0002

Data Index: 396485 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0899. Min Act: -0.0002

Data Index: 309364 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1220679 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0835. Min Act: -0.0002

Data Index: 810898 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0776. Min Act: -0.0002

Data Index: 761299 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0800. Min Act: -0.0002

Data Index: 124538 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0790. Min Act: -0.0002

Data Index: 76362 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0792. Min Act: -0.0002

Data Index: 248197 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0761. Min Act: -0.0002

Data Index: 909064 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0756. Min Act: -0.0002

Data Index: 965115 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0747. Min Act: -0.0002

Data Index: 945398 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0796. Min Act: -0.0002

Data Index: 157670 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0711. Min Act: -0.0002

Data Index: 305520 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0725. Min Act: -0.0002

Data Index: 970577 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0758. Min Act: -0.0002

Data Index: 144078 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0719. Min Act: -0.0002

Data Index: 924592 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0725. Min Act: -0.0002

Data Index: 661251 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0687. Min Act: -0.0002

Data Index: 754063 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1058647 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0734. Min Act: -0.0002

Data Index: 637411 (C4 (Web Text))

Max Activating Token Index: 898