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

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

Neuron 4101 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3747. Min Act: -0.0001

Data Index: 904863 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3162. Min Act: -0.0001

Data Index: 281403 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3254. Min Act: -0.0001

Data Index: 175715 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3178. Min Act: -0.0001

Data Index: 1225668 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3089. Min Act: -0.0001

Data Index: 606444 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1358067 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3399. Min Act: -0.0001

Data Index: 948248 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2854. Min Act: -0.0001

Data Index: 702648 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3022. Min Act: -0.0001

Data Index: 466769 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2619. Min Act: -0.0001

Data Index: 273941 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1063258 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1017199 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2716. Min Act: -0.0001

Data Index: 519699 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2646. Min Act: -0.0001

Data Index: 591030 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2605. Min Act: -0.0001

Data Index: 315697 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2670. Min Act: -0.0001

Data Index: 55036 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1333770 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2440. Min Act: -0.0001

Data Index: 376559 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2552. Min Act: -0.0000

Data Index: 558135 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2636. Min Act: -0.0001

Data Index: 853092 (C4 (Web Text))

Max Activating Token Index: 130