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

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

Neuron 1592 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.5112. Min Act: -0.0000

Data Index: 783285 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.5215. Min Act: -0.0000

Data Index: 207970 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4700. Min Act: -0.0000

Data Index: 970356 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.5149. Min Act: -0.0000

Data Index: 645418 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.5104. Min Act: -0.0000

Data Index: 164095 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4936. Min Act: -0.0000

Data Index: 571790 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.5260. Min Act: -0.0000

Data Index: 125973 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1093068 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4815. Min Act: -0.0000

Data Index: 481970 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4976. Min Act: -0.0000

Data Index: 397772 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1302358 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4750. Min Act: -0.0000

Data Index: 894786 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1069968 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1186653 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1226022 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4742. Min Act: -0.0000

Data Index: 995365 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4511. Min Act: -0.0000

Data Index: 28218 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1246233 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1263023 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.5116. Min Act: -0.0000

Data Index: 471460 (C4 (Web Text))

Max Activating Token Index: 206