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

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

Neuron 1320 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.9427. Min Act: -0.0000

Data Index: 1616016 (Python Code)

Max Activating Token Index: 315

Text #1

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.7424. Min Act: -0.0000

Data Index: 1600270 (Python Code)

Max Activating Token Index: 775

Text #2

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.6470. Min Act: -0.0000

Data Index: 1404828 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.6377. Min Act: -0.0000

Data Index: 1631012 (Python Code)

Max Activating Token Index: 852

Text #4

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.4714. Min Act: -0.0000

Data Index: 1627428 (Python Code)

Max Activating Token Index: 570

Text #5

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.4356. Min Act: -0.0000

Data Index: 1453092 (Python Code)

Max Activating Token Index: 307

Text #6

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1403647 (Python Code)

Max Activating Token Index: 266

Text #7

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1540626 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1462080 (Python Code)

Max Activating Token Index: 850

Text #9

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.5062. Min Act: -0.0000

Data Index: 1631203 (Python Code)

Max Activating Token Index: 920

Text #10

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.4492. Min Act: -0.0000

Data Index: 1599073 (Python Code)

Max Activating Token Index: 513

Text #11

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.2268. Min Act: -0.0000

Data Index: 1483256 (Python Code)

Max Activating Token Index: 747

Text #12

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1416087 (Python Code)

Max Activating Token Index: 260

Text #13

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1432957 (Python Code)

Max Activating Token Index: 679

Text #14

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.2584. Min Act: -0.0000

Data Index: 1419756 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.2688. Min Act: -0.0000

Data Index: 693961 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.2965. Min Act: -0.0000

Data Index: 602905 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1565383 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1579231 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 1.9427. Min Range: -1.9427

Max Act: 1.3546. Min Act: -0.0000

Data Index: 1506880 (Python Code)

Max Activating Token Index: 558