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

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

Neuron 4673 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1860. Min Range: -1.1860

Max Act: 1.1738. Min Act: -0.0000

Data Index: 789920 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 1.1860. Min Range: -1.1860

Max Act: 1.0505. Min Act: -0.0000

Data Index: 836487 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 1.1860. Min Range: -1.1860

Max Act: 1.1860. Min Act: -0.0000

Data Index: 450474 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9274. Min Act: -0.0000

Data Index: 866064 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9798. Min Act: -0.0000

Data Index: 39885 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9988. Min Act: -0.0000

Data Index: 152322 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1131558 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9909. Min Act: -0.0000

Data Index: 746131 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1102870 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9493. Min Act: -0.0000

Data Index: 74798 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1233295 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9208. Min Act: -0.0000

Data Index: 68924 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1145449 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1046292 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9101. Min Act: -0.0000

Data Index: 927882 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9842. Min Act: -0.0000

Data Index: 475118 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1340936 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8649. Min Act: -0.0000

Data Index: 882412 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9118. Min Act: -0.0000

Data Index: 537743 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1101253 (C4 (Web Text))

Max Activating Token Index: 715