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

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

Neuron 1854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7007. Min Range: -1.7007

Max Act: 1.7007. Min Act: -0.0000

Data Index: 515807 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.7007. Min Range: -1.7007

Max Act: 1.0993. Min Act: -0.0000

Data Index: 1143780 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 1.7007. Min Range: -1.7007

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1217694 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.9577. Min Act: -0.0000

Data Index: 141690 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.7007. Min Range: -1.7007

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1089057 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.7007. Min Range: -1.7007

Max Act: 1.0296. Min Act: -0.0000

Data Index: 813952 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.9004. Min Act: -0.0000

Data Index: 240621 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 1.7007. Min Range: -1.7007

Max Act: 1.0107. Min Act: -0.0000

Data Index: 209714 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1150224 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.7640. Min Act: -0.0000

Data Index: 240807 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.8181. Min Act: -0.0000

Data Index: 735344 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.8914. Min Act: -0.0000

Data Index: 279422 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1066225 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1304784 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.8744. Min Act: -0.0000

Data Index: 34213 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1302097 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.8098. Min Act: -0.0000

Data Index: 513068 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.7937. Min Act: -0.0000

Data Index: 774612 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1144244 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.7007. Min Range: -1.7007

Max Act: 0.6785. Min Act: -0.0000

Data Index: 724889 (C4 (Web Text))

Max Activating Token Index: 935