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

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

Neuron 198 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: 0.7357. Min Range: -0.7357

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1320891 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.6539. Min Act: -0.0000

Data Index: 138513 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5886. Min Act: -0.0000

Data Index: 871233 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1047971 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.6071. Min Act: -0.0000

Data Index: 43174 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5538. Min Act: -0.0000

Data Index: 912934 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1289041 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5492. Min Act: -0.0000

Data Index: 145934 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5745. Min Act: -0.0000

Data Index: 761906 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5705. Min Act: -0.0000

Data Index: 691186 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5555. Min Act: -0.0000

Data Index: 216196 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5768. Min Act: -0.0000

Data Index: 590271 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1955 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5533. Min Act: -0.0000

Data Index: 881048 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5496. Min Act: -0.0000

Data Index: 768153 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5366. Min Act: -0.0000

Data Index: 330612 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5058. Min Act: 0.0000

Data Index: 558945 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1054095 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5096. Min Act: 0.0000

Data Index: 369065 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5235. Min Act: -0.0000

Data Index: 378847 (C4 (Web Text))

Max Activating Token Index: 110