Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4072 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5882. Min Act: -0.0001

Data Index: 693679 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5852. Min Act: -0.0001

Data Index: 23614 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.6209. Min Act: -0.0001

Data Index: 1077844 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5940. Min Act: -0.0001

Data Index: 1185150 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.6289. Min Act: -0.0001

Data Index: 608617 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5280. Min Act: -0.0001

Data Index: 628099 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5763. Min Act: -0.0001

Data Index: 889614 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5600. Min Act: -0.0001

Data Index: 833724 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5228. Min Act: -0.0001

Data Index: 436008 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1037007 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5366. Min Act: -0.0001

Data Index: 496392 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5326. Min Act: -0.0001

Data Index: 118316 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5281. Min Act: -0.0001

Data Index: 1175266 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5151. Min Act: -0.0001

Data Index: 651591 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5140. Min Act: -0.0001

Data Index: 926965 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5156. Min Act: -0.0001

Data Index: 536960 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5081. Min Act: -0.0001

Data Index: 463298 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.4718. Min Act: -0.0001

Data Index: 236170 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.4775. Min Act: -0.0001

Data Index: 273127 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.6289. Min Range: -0.6289

Max Act: 0.5109. Min Act: -0.0001

Data Index: 408266 (C4 (Web Text))

Max Activating Token Index: 768