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

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

Neuron 1620 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: 1.0754. Min Range: -1.0754

Max Act: 1.0754. Min Act: -0.0000

Data Index: 140873 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 1.0754. Min Range: -1.0754

Max Act: 1.0163. Min Act: -0.0000

Data Index: 32239 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9274. Min Act: -0.0000

Data Index: 384453 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1191976 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9101. Min Act: -0.0000

Data Index: 166476 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8866. Min Act: -0.0000

Data Index: 184129 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7850. Min Act: 0.0000

Data Index: 1237395 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1116132 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7421. Min Act: -0.0000

Data Index: 61792 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7393. Min Act: -0.0000

Data Index: 690099 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6999. Min Act: -0.0000

Data Index: 513095 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7398. Min Act: -0.0000

Data Index: 570477 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7009. Min Act: -0.0000

Data Index: 918907 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6762. Min Act: -0.0000

Data Index: 550428 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6966. Min Act: -0.0000

Data Index: 900827 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6940. Min Act: -0.0000

Data Index: 361407 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6655. Min Act: -0.0000

Data Index: 507369 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6825. Min Act: -0.0000

Data Index: 765959 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6753. Min Act: -0.0000

Data Index: 372634 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6639. Min Act: -0.0000

Data Index: 496025 (C4 (Web Text))

Max Activating Token Index: 65