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

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

Neuron 4418 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7827. Min Act: -0.0000

Data Index: 736171 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6042. Min Act: -0.0000

Data Index: 908479 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1217720 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5931. Min Act: -0.0000

Data Index: 529519 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6547. Min Act: -0.0000

Data Index: 474864 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6044. Min Act: -0.0000

Data Index: 269907 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6353. Min Act: -0.0000

Data Index: 690048 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6186. Min Act: -0.0000

Data Index: 142405 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5794. Min Act: -0.0000

Data Index: 652219 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6730. Min Act: -0.0000

Data Index: 150719 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5772. Min Act: -0.0000

Data Index: 626387 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1206692 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5239. Min Act: -0.0000

Data Index: 557952 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6017. Min Act: -0.0000

Data Index: 19778 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5725. Min Act: -0.0000

Data Index: 833388 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5788. Min Act: -0.0000

Data Index: 917852 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5522. Min Act: -0.0000

Data Index: 697362 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5381. Min Act: -0.0000

Data Index: 252346 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5638. Min Act: -0.0000

Data Index: 985578 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.4449. Min Act: -0.0000

Data Index: 195205 (C4 (Web Text))

Max Activating Token Index: 1019