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

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

Neuron 80 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.8079. Min Act: -0.0001

Data Index: 485057 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6768. Min Act: -0.0001

Data Index: 1300827 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6781. Min Act: -0.0001

Data Index: 1225812 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6613. Min Act: -0.0001

Data Index: 145424 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6089. Min Act: -0.0001

Data Index: 441422 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5500. Min Act: -0.0001

Data Index: 866337 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5990. Min Act: -0.0001

Data Index: 606155 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5735. Min Act: -0.0001

Data Index: 849146 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5686. Min Act: -0.0001

Data Index: 549553 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5547. Min Act: -0.0001

Data Index: 741874 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5116. Min Act: -0.0001

Data Index: 45734 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.4688. Min Act: -0.0001

Data Index: 729204 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5319. Min Act: -0.0001

Data Index: 878471 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5116. Min Act: -0.0001

Data Index: 849677 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.4915. Min Act: -0.0001

Data Index: 702872 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5246. Min Act: -0.0001

Data Index: 1197733 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.4765. Min Act: -0.0001

Data Index: 511316 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5368. Min Act: -0.0001

Data Index: 1033411 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.4979. Min Act: -0.0001

Data Index: 952224 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5182. Min Act: -0.0001

Data Index: 250426 (C4 (Web Text))

Max Activating Token Index: 700