Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 809 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1803. Min Act: -0.0001

Data Index: 789654 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1830. Min Act: -0.0001

Data Index: 92406 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1727. Min Act: -0.0001

Data Index: 651741 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1741. Min Act: -0.0001

Data Index: 777172 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1648. Min Act: -0.0001

Data Index: 274673 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1596. Min Act: -0.0001

Data Index: 119338 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1349912 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1628. Min Act: -0.0001

Data Index: 861473 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1067524 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1430. Min Act: -0.0001

Data Index: 621999 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1585. Min Act: -0.0001

Data Index: 919910 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1398. Min Act: -0.0001

Data Index: 11365 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1454. Min Act: -0.0001

Data Index: 270052 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1507. Min Act: -0.0001

Data Index: 721193 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1496. Min Act: -0.0001

Data Index: 374337 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1431. Min Act: -0.0001

Data Index: 998169 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1548. Min Act: -0.0001

Data Index: 263401 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1490. Min Act: -0.0001

Data Index: 563652 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1493. Min Act: -0.0001

Data Index: 554850 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1543. Min Act: -0.0001

Data Index: 887439 (C4 (Web Text))

Max Activating Token Index: 495