Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3367 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.7313. Min Act: -0.0002

Data Index: 887865 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.5897. Min Act: -0.0001

Data Index: 572308 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.5728. Min Act: -0.0002

Data Index: 225732 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.5992. Min Act: -0.0002

Data Index: 975176 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.5126. Min Act: -0.0002

Data Index: 1236413 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.5194. Min Act: -0.0001

Data Index: 158392 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.3944. Min Act: -0.0001

Data Index: 1176236 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4618. Min Act: -0.0002

Data Index: 1097183 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4927. Min Act: -0.0002

Data Index: 843472 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.5045. Min Act: -0.0001

Data Index: 1355687 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4372. Min Act: -0.0001

Data Index: 338477 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4595. Min Act: -0.0001

Data Index: 705254 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.3830. Min Act: -0.0001

Data Index: 195214 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4422. Min Act: -0.0001

Data Index: 463659 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4681. Min Act: -0.0002

Data Index: 870339 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4633. Min Act: -0.0002

Data Index: 1060173 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4650. Min Act: -0.0002

Data Index: 548032 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4298. Min Act: -0.0002

Data Index: 660556 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.4308. Min Act: -0.0001

Data Index: 1349288 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.3796. Min Act: -0.0001

Data Index: 63874 (C4 (Web Text))

Max Activating Token Index: 677