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

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

Neuron 4538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6818. Min Act: -0.0000

Data Index: 742673 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6418. Min Act: -0.0000

Data Index: 412815 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5837. Min Act: -0.0000

Data Index: 667285 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5908. Min Act: -0.0000

Data Index: 854893 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6160. Min Act: -0.0000

Data Index: 815040 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1352688 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1062745 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4781. Min Act: -0.0000

Data Index: 520958 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1295927 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5038. Min Act: -0.0000

Data Index: 701542 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1095520 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4953. Min Act: -0.0000

Data Index: 329887 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1076197 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4208. Min Act: -0.0000

Data Index: 256110 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4921. Min Act: -0.0000

Data Index: 550782 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4564. Min Act: -0.0000

Data Index: 586607 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4386. Min Act: -0.0000

Data Index: 23868 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4539. Min Act: -0.0000

Data Index: 696535 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4671. Min Act: -0.0000

Data Index: 499663 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4516. Min Act: -0.0000

Data Index: 240500 (C4 (Web Text))

Max Activating Token Index: 366