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

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

Neuron 2483 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: 1.6045. Min Range: -1.6045

Max Act: 1.6045. Min Act: -0.0000

Data Index: 856907 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.4743. Min Act: -0.0000

Data Index: 728421 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.3168. Min Act: -0.0000

Data Index: 504286 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.2167. Min Act: -0.0000

Data Index: 152867 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1806. Min Act: -0.0000

Data Index: 776932 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1521. Min Act: -0.0000

Data Index: 111900 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1676. Min Act: -0.0000

Data Index: 808574 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1162653 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1313. Min Act: -0.0000

Data Index: 1054210 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1237. Min Act: -0.0000

Data Index: 189785 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1499. Min Act: -0.0000

Data Index: 930334 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1234391 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1114984 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1014. Min Act: -0.0000

Data Index: 939604 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1330895 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1136315 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.1027. Min Act: -0.0001

Data Index: 44399 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.0910. Min Act: -0.0000

Data Index: 82021 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1087228 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 1.6045. Min Range: -1.6045

Max Act: 1.0249. Min Act: -0.0000

Data Index: 445961 (C4 (Web Text))

Max Activating Token Index: 241