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

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

Neuron 2355 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: 1.8622. Min Range: -1.8622

Max Act: 1.6801. Min Act: -0.0000

Data Index: 212479 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.7533. Min Act: -0.0000

Data Index: 974056 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.7057. Min Act: -0.0000

Data Index: 762879 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.8622. Min Act: -0.0000

Data Index: 638304 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3605. Min Act: -0.0000

Data Index: 278570 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.5470. Min Act: -0.0000

Data Index: 1043822 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4487. Min Act: -0.0000

Data Index: 832014 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1037550 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.5236. Min Act: -0.0000

Data Index: 493172 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4961. Min Act: -0.0000

Data Index: 631113 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.5899. Min Act: -0.0000

Data Index: 278794 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4721. Min Act: -0.0000

Data Index: 892429 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4748. Min Act: -0.0000

Data Index: 329590 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1019523 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4134. Min Act: -0.0000

Data Index: 911958 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4077. Min Act: -0.0000

Data Index: 131076 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3211. Min Act: -0.0000

Data Index: 760307 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3141. Min Act: -0.0000

Data Index: 249443 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3742. Min Act: -0.0000

Data Index: 822573 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4749. Min Act: -0.0000

Data Index: 735371 (C4 (Web Text))

Max Activating Token Index: 81