Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3702 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8818. Min Act: -0.0001

Data Index: 766793 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8674. Min Act: -0.0002

Data Index: 223256 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8598. Min Act: -0.0001

Data Index: 1119538 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.9905. Min Act: -0.0001

Data Index: 992109 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8224. Min Act: -0.0001

Data Index: 922203 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7993. Min Act: -0.0002

Data Index: 833540 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.8223. Min Act: -0.0002

Data Index: 853897 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7536. Min Act: -0.0001

Data Index: 771680 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7438. Min Act: -0.0001

Data Index: 842925 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7295. Min Act: -0.0002

Data Index: 512183 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6647. Min Act: -0.0001

Data Index: 951893 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7267. Min Act: -0.0001

Data Index: 1049664 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7219. Min Act: -0.0001

Data Index: 613369 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6885. Min Act: -0.0001

Data Index: 249771 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7493. Min Act: -0.0002

Data Index: 764087 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6841. Min Act: -0.0002

Data Index: 660227 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6579. Min Act: -0.0002

Data Index: 635446 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6720. Min Act: -0.0001

Data Index: 453719 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7185. Min Act: -0.0001

Data Index: 174264 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6734. Min Act: -0.0001

Data Index: 114929 (C4 (Web Text))

Max Activating Token Index: 323