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

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

Neuron 3722 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.7022. Min Act: -0.0000

Data Index: 1299070 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.5859. Min Act: -0.0000

Data Index: 128262 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.6572. Min Act: -0.0000

Data Index: 748638 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.6778. Min Act: -0.0000

Data Index: 199139 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.5702. Min Act: -0.0000

Data Index: 477854 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.4641. Min Act: -0.0000

Data Index: 598497 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.4689. Min Act: -0.0000

Data Index: 1083988 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.5263. Min Act: -0.0000

Data Index: 376854 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.4489. Min Act: -0.0000

Data Index: 903253 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.4490. Min Act: -0.0000

Data Index: 640742 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.4433. Min Act: -0.0000

Data Index: 525800 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.3569. Min Act: -0.0000

Data Index: 351219 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.3613. Min Act: -0.0000

Data Index: 882747 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.5040. Min Act: -0.0000

Data Index: 492852 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1191204 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.3263. Min Act: -0.0000

Data Index: 498589 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.2162. Min Act: -0.0000

Data Index: 117947 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.2238. Min Act: -0.0000

Data Index: 373782 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.3518. Min Act: -0.0000

Data Index: 830850 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 1.7022. Min Range: -1.7022

Max Act: 1.3428. Min Act: -0.0000

Data Index: 933077 (C4 (Web Text))

Max Activating Token Index: 551