Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2444 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6001. Min Act: -0.0001

Data Index: 978944 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5737. Min Act: -0.0001

Data Index: 130780 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6136. Min Act: -0.0001

Data Index: 158189 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6249. Min Act: -0.0001

Data Index: 814667 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5543. Min Act: -0.0001

Data Index: 1287099 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5530. Min Act: -0.0001

Data Index: 1104569 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5592. Min Act: -0.0001

Data Index: 1246210 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5326. Min Act: -0.0001

Data Index: 367147 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5556. Min Act: -0.0001

Data Index: 406866 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5601. Min Act: -0.0001

Data Index: 989701 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5329. Min Act: -0.0001

Data Index: 1179911 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5072. Min Act: -0.0001

Data Index: 336261 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5007. Min Act: -0.0001

Data Index: 1052604 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5162. Min Act: -0.0001

Data Index: 517354 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5326. Min Act: -0.0001

Data Index: 824062 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5138. Min Act: -0.0001

Data Index: 722069 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4296. Min Act: -0.0001

Data Index: 248980 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5083. Min Act: -0.0001

Data Index: 43884 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5024. Min Act: -0.0001

Data Index: 1048442 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5339. Min Act: -0.0001

Data Index: 925484 (C4 (Web Text))

Max Activating Token Index: 272