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

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

Neuron 450 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: 1.1396. Min Range: -1.1396

Max Act: 1.0770. Min Act: -0.0001

Data Index: 1150944 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 1.1396. Min Range: -1.1396

Max Act: 1.1396. Min Act: -0.0001

Data Index: 498367 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 1.1396. Min Range: -1.1396

Max Act: 1.0620. Min Act: -0.0001

Data Index: 170631 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 1.1396. Min Range: -1.1396

Max Act: 1.0005. Min Act: -0.0001

Data Index: 124632 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.9814. Min Act: -0.0001

Data Index: 104548 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.9142. Min Act: -0.0001

Data Index: 960033 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8951. Min Act: -0.0001

Data Index: 379992 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8081. Min Act: -0.0001

Data Index: 691101 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.9176. Min Act: -0.0001

Data Index: 309712 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8302. Min Act: -0.0001

Data Index: 1043868 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.9056. Min Act: -0.0001

Data Index: 862903 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.7724. Min Act: -0.0001

Data Index: 1171972 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8883. Min Act: -0.0001

Data Index: 890949 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8180. Min Act: -0.0001

Data Index: 987451 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8366. Min Act: -0.0001

Data Index: 1291237 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8590. Min Act: -0.0001

Data Index: 820148 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8328. Min Act: -0.0001

Data Index: 69296 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8500. Min Act: -0.0001

Data Index: 244306 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8583. Min Act: -0.0001

Data Index: 749681 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 1.1396. Min Range: -1.1396

Max Act: 0.8534. Min Act: -0.0001

Data Index: 388058 (C4 (Web Text))

Max Activating Token Index: 670