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

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

Neuron 5719 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.9301. Min Act: -0.0000

Data Index: 1170279 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.9292. Min Act: -0.0000

Data Index: 857315 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1073818 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.6980. Min Act: -0.0000

Data Index: 576795 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.3638. Min Act: -0.0000

Data Index: 418574 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.3619. Min Act: -0.0000

Data Index: 556544 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1275368 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1075600 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.3215. Min Act: -0.0000

Data Index: 217793 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.2741. Min Act: 0.0000

Data Index: 1007880 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.2005. Min Act: -0.0000

Data Index: 317026 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.2646. Min Act: -0.0000

Data Index: 761497 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.2333. Min Act: -0.0000

Data Index: 257364 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.2264. Min Act: -0.0000

Data Index: 784726 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1087431 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.2032. Min Act: -0.0000

Data Index: 1121197 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.1836. Min Act: -0.0000

Data Index: 862140 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1038149 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.1661. Min Act: -0.0000

Data Index: 589639 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 1.9301. Min Range: -1.9301

Max Act: 1.1424. Min Act: -0.0000

Data Index: 726913 (C4 (Web Text))

Max Activating Token Index: 491