Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1520 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9805. Min Act: -0.0001

Data Index: 235733 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8882. Min Act: -0.0001

Data Index: 1584794 (Python Code)

Max Activating Token Index: 334

Text #2

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8652. Min Act: -0.0001

Data Index: 787502 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8294. Min Act: -0.0001

Data Index: 771184 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8789. Min Act: -0.0001

Data Index: 1029820 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8173. Min Act: -0.0001

Data Index: 1143278 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8381. Min Act: -0.0001

Data Index: 1082307 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7995. Min Act: -0.0001

Data Index: 1409554 (Python Code)

Max Activating Token Index: 634

Text #8

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7984. Min Act: -0.0001

Data Index: 618240 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7605. Min Act: -0.0001

Data Index: 1528879 (Python Code)

Max Activating Token Index: 725

Text #10

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7747. Min Act: -0.0001

Data Index: 1655615 (Python Code)

Max Activating Token Index: 534

Text #11

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7888. Min Act: -0.0001

Data Index: 982567 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7860. Min Act: -0.0001

Data Index: 704942 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7659. Min Act: -0.0001

Data Index: 329592 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7780. Min Act: -0.0001

Data Index: 1365790 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7516. Min Act: -0.0001

Data Index: 447275 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7263. Min Act: -0.0001

Data Index: 354866 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7200. Min Act: -0.0001

Data Index: 272648 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7396. Min Act: -0.0001

Data Index: 934383 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7127. Min Act: -0.0001

Data Index: 1549227 (Python Code)

Max Activating Token Index: 943