Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3594 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3914. Min Act: -0.0000

Data Index: 71923 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3343. Min Act: -0.0000

Data Index: 13571 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1428600 (Python Code)

Max Activating Token Index: 406

Text #3

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2995. Min Act: -0.0000

Data Index: 355945 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2886. Min Act: -0.0000

Data Index: 91137 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1034649 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2607. Min Act: -0.0000

Data Index: 425995 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1172853 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1518276 (Python Code)

Max Activating Token Index: 336

Text #9

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1058903 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2773. Min Act: -0.0000

Data Index: 678898 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2851. Min Act: -0.0000

Data Index: 823701 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1198536 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2834. Min Act: -0.0000

Data Index: 330795 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1427006 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1608080 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2533. Min Act: -0.0000

Data Index: 3181 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1472432 (Python Code)

Max Activating Token Index: 909

Text #18

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2499. Min Act: -0.0000

Data Index: 562238 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1642947 (Python Code)

Max Activating Token Index: 369