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

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

Neuron 4847 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: 2.1636. Min Range: -2.1636

Max Act: 2.1018. Min Act: -0.0000

Data Index: 738273 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 2.1636. Min Range: -2.1636

Max Act: 2.1636. Min Act: -0.0000

Data Index: 465512 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 2.1636. Min Range: -2.1636

Max Act: 2.0080. Min Act: -0.0000

Data Index: 1187637 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 2.1636. Min Range: -2.1636

Max Act: 2.1241. Min Act: -0.0001

Data Index: 211878 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.8679. Min Act: -0.0001

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.9441. Min Act: -0.0000

Data Index: 542766 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.9295. Min Act: -0.0000

Data Index: 920283 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.8636. Min Act: -0.0000

Data Index: 1346177 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.8192. Min Act: -0.0000

Data Index: 1268204 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.7222. Min Act: -0.0000

Data Index: 618584 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.7809. Min Act: -0.0000

Data Index: 726828 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.7605. Min Act: -0.0001

Data Index: 1112246 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.6563. Min Act: -0.0000

Data Index: 204734 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.5735. Min Act: -0.0001

Data Index: 566692 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.6783. Min Act: -0.0001

Data Index: 226416 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.6454. Min Act: -0.0000

Data Index: 432679 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.7319. Min Act: -0.0000

Data Index: 874366 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.7298. Min Act: -0.0001

Data Index: 959890 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.7069. Min Act: -0.0000

Data Index: 1314240 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 2.1636. Min Range: -2.1636

Max Act: 1.8232. Min Act: -0.0000

Data Index: 496848 (C4 (Web Text))

Max Activating Token Index: 318