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

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

Neuron 3719 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.8686. Min Act: -0.0001

Data Index: 1115682 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7995. Min Act: -0.0001

Data Index: 1023262 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.8321. Min Act: -0.0001

Data Index: 1049325 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.8170. Min Act: -0.0001

Data Index: 1258709 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7281. Min Act: -0.0001

Data Index: 843260 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7684. Min Act: -0.0001

Data Index: 355883 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7544. Min Act: -0.0001

Data Index: 435055 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7609. Min Act: -0.0001

Data Index: 1204160 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7708. Min Act: -0.0001

Data Index: 1058735 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7229. Min Act: -0.0001

Data Index: 352851 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6923. Min Act: -0.0001

Data Index: 974739 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7390. Min Act: -0.0001

Data Index: 215182 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7110. Min Act: -0.0001

Data Index: 211778 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7526. Min Act: -0.0001

Data Index: 590396 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7822. Min Act: -0.0001

Data Index: 905571 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6723. Min Act: -0.0001

Data Index: 641580 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6971. Min Act: -0.0001

Data Index: 486462 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7066. Min Act: -0.0001

Data Index: 849174 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6673. Min Act: -0.0001

Data Index: 342163 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6492. Min Act: -0.0001

Data Index: 419270 (C4 (Web Text))

Max Activating Token Index: 495