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

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

Neuron 564 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0000

Data Index: 904108 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0984. Min Act: -0.0000

Data Index: 889411 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0822. Min Act: -0.0000

Data Index: 890882 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0874. Min Act: -0.0000

Data Index: 244868 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0807. Min Act: -0.0000

Data Index: 370014 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0778. Min Act: -0.0000

Data Index: 22778 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1077227 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1012435 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1237149 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1128261 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0670. Min Act: -0.0000

Data Index: 369387 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1209287 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0680. Min Act: -0.0000

Data Index: 462520 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0641. Min Act: -0.0000

Data Index: 25239 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0671. Min Act: -0.0000

Data Index: 715843 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0723. Min Act: -0.0000

Data Index: 871092 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0693. Min Act: -0.0000

Data Index: 931220 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0684. Min Act: -0.0000

Data Index: 449202 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0648. Min Act: -0.0000

Data Index: 25843 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0631. Min Act: -0.0000

Data Index: 54253 (C4 (Web Text))

Max Activating Token Index: 254