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

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

Neuron 5022 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3747. Min Range: -4.3747

Max Act: 4.3747. Min Act: -0.0000

Data Index: 705558 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 4.3747. Min Range: -4.3747

Max Act: 4.1636. Min Act: -0.0000

Data Index: 396011 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 4.3747. Min Range: -4.3747

Max Act: 3.9051. Min Act: -0.0000

Data Index: 798506 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 4.3747. Min Range: -4.3747

Max Act: 3.7087. Min Act: -0.0000

Data Index: 460584 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 4.3747. Min Range: -4.3747

Max Act: 3.6841. Min Act: -0.0000

Data Index: 1229754 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 4.3747. Min Range: -4.3747

Max Act: 3.6470. Min Act: -0.0000

Data Index: 873584 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 4.3747. Min Range: -4.3747

Max Act: 3.4355. Min Act: -0.0000

Data Index: 709840 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 4.3747. Min Range: -4.3747

Max Act: 3.2906. Min Act: -0.0000

Data Index: 957812 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 4.3747. Min Range: -4.3747

Max Act: 3.3661. Min Act: -0.0000

Data Index: 506744 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 4.3747. Min Range: -4.3747

Max Act: 3.2489. Min Act: -0.0000

Data Index: 1244786 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 4.3747. Min Range: -4.3747

Max Act: 2.9134. Min Act: -0.0000

Data Index: 905424 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 4.3747. Min Range: -4.3747

Max Act: 3.3187. Min Act: -0.0000

Data Index: 979732 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 4.3747. Min Range: -4.3747

Max Act: 2.9611. Min Act: -0.0000

Data Index: 302137 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 4.3747. Min Range: -4.3747

Max Act: 2.7756. Min Act: -0.0000

Data Index: 545550 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 4.3747. Min Range: -4.3747

Max Act: 2.7243. Min Act: -0.0000

Data Index: 294830 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 4.3747. Min Range: -4.3747

Max Act: 2.6873. Min Act: -0.0000

Data Index: 301510 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 4.3747. Min Range: -4.3747

Max Act: 2.7588. Min Act: -0.0000

Data Index: 363690 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 4.3747. Min Range: -4.3747

Max Act: 2.7320. Min Act: -0.0000

Data Index: 1250616 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 4.3747. Min Range: -4.3747

Max Act: 2.7231. Min Act: -0.0000

Data Index: 1267387 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 4.3747. Min Range: -4.3747

Max Act: 2.7075. Min Act: -0.0000

Data Index: 237677 (C4 (Web Text))

Max Activating Token Index: 668