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

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

Neuron 4477 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.9545. Min Act: -0.0001

Data Index: 600282 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.5880. Min Act: -0.0001

Data Index: 74795 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.2461. Min Act: -0.0001

Data Index: 845299 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.5384. Min Act: -0.0001

Data Index: 85574 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.0796. Min Act: -0.0001

Data Index: 344374 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.1738. Min Act: -0.0001

Data Index: 268132 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.1631. Min Act: -0.0001

Data Index: 367464 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.1139. Min Act: -0.0001

Data Index: 696526 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.1608. Min Act: -0.0001

Data Index: 635547 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.0269. Min Act: -0.0001

Data Index: 1109661 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 2.9545. Min Range: -2.9545

Max Act: 1.9407. Min Act: -0.0001

Data Index: 664131 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.2534. Min Act: -0.0001

Data Index: 853274 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 2.9545. Min Range: -2.9545

Max Act: 1.9205. Min Act: -0.0001

Data Index: 340895 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.1137. Min Act: -0.0001

Data Index: 1257308 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.0995. Min Act: -0.0001

Data Index: 645002 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 2.9545. Min Range: -2.9545

Max Act: 1.9293. Min Act: -0.0001

Data Index: 138740 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 2.9545. Min Range: -2.9545

Max Act: 1.8325. Min Act: -0.0001

Data Index: 957303 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 2.9545. Min Range: -2.9545

Max Act: 1.8880. Min Act: -0.0001

Data Index: 1057050 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 2.9545. Min Range: -2.9545

Max Act: 1.8758. Min Act: -0.0001

Data Index: 343733 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 2.9545. Min Range: -2.9545

Max Act: 1.8501. Min Act: -0.0001

Data Index: 1027977 (C4 (Web Text))

Max Activating Token Index: 335