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

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

Neuron 1646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9758. Min Range: -3.9758

Max Act: 3.9758. Min Act: -0.0000

Data Index: 1111763 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 3.9758. Min Range: -3.9758

Max Act: 3.8134. Min Act: -0.0000

Data Index: 1165522 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 3.9758. Min Range: -3.9758

Max Act: 3.8661. Min Act: -0.0000

Data Index: 912896 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 3.9758. Min Range: -3.9758

Max Act: 3.3993. Min Act: -0.0000

Data Index: 1071747 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 3.9758. Min Range: -3.9758

Max Act: 3.4252. Min Act: -0.0000

Data Index: 470149 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 3.9758. Min Range: -3.9758

Max Act: 3.1714. Min Act: -0.0000

Data Index: 1273803 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 3.9758. Min Range: -3.9758

Max Act: 3.1129. Min Act: -0.0000

Data Index: 955003 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 3.9758. Min Range: -3.9758

Max Act: 3.0431. Min Act: -0.0000

Data Index: 1298831 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 3.9758. Min Range: -3.9758

Max Act: 3.0380. Min Act: -0.0000

Data Index: 1063267 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.9804. Min Act: -0.0000

Data Index: 1347046 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.8221. Min Act: -0.0000

Data Index: 490432 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.9291. Min Act: -0.0000

Data Index: 271384 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.9166. Min Act: -0.0000

Data Index: 1021 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.8762. Min Act: -0.0000

Data Index: 599198 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.7729. Min Act: -0.0000

Data Index: 959875 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.9238. Min Act: -0.0000

Data Index: 567869 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.9059. Min Act: -0.0000

Data Index: 355807 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.9045. Min Act: -0.0000

Data Index: 1267076 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.4541. Min Act: -0.0000

Data Index: 1216578 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 3.9758. Min Range: -3.9758

Max Act: 2.7067. Min Act: -0.0000

Data Index: 1028008 (C4 (Web Text))

Max Activating Token Index: 402