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

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

Neuron 4758 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5626. Min Range: -7.5626

Max Act: 7.5626. Min Act: -0.0001

Data Index: 803076 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 7.5626. Min Range: -7.5626

Max Act: 6.7764. Min Act: -0.0000

Data Index: 1238722 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 7.5626. Min Range: -7.5626

Max Act: 6.6726. Min Act: -0.0000

Data Index: 1282078 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 7.5626. Min Range: -7.5626

Max Act: 6.7711. Min Act: -0.0000

Data Index: 1077277 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 7.5626. Min Range: -7.5626

Max Act: 6.2985. Min Act: -0.0000

Data Index: 1138493 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 7.5626. Min Range: -7.5626

Max Act: 6.2421. Min Act: -0.0000

Data Index: 690105 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 7.5626. Min Range: -7.5626

Max Act: 6.2876. Min Act: -0.0000

Data Index: 700207 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 7.5626. Min Range: -7.5626

Max Act: 6.0090. Min Act: -0.0000

Data Index: 217822 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 7.5626. Min Range: -7.5626

Max Act: 6.1003. Min Act: -0.0000

Data Index: 714042 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.7000. Min Act: -0.0000

Data Index: 1312968 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.8427. Min Act: -0.0000

Data Index: 43172 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.9504. Min Act: -0.0000

Data Index: 1285242 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.5308. Min Act: -0.0000

Data Index: 499368 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.8911. Min Act: -0.0000

Data Index: 212835 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.6736. Min Act: -0.0000

Data Index: 155664 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.6776. Min Act: -0.0000

Data Index: 522874 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.4340. Min Act: -0.0000

Data Index: 715001 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.5622. Min Act: -0.0000

Data Index: 823935 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.5590. Min Act: -0.0000

Data Index: 62823 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 7.5626. Min Range: -7.5626

Max Act: 5.7346. Min Act: -0.0000

Data Index: 471421 (C4 (Web Text))

Max Activating Token Index: 989