Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3642 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6597. Min Act: -0.0001

Data Index: 747423 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.7269. Min Act: -0.0001

Data Index: 117678 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6658. Min Act: -0.0001

Data Index: 920701 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6229. Min Act: -0.0002

Data Index: 719468 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6721. Min Act: -0.0001

Data Index: 153219 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6697. Min Act: -0.0001

Data Index: 1241508 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6358. Min Act: -0.0001

Data Index: 793690 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5816. Min Act: -0.0001

Data Index: 1156388 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5941. Min Act: -0.0001

Data Index: 1230995 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5863. Min Act: -0.0001

Data Index: 809217 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6011. Min Act: -0.0001

Data Index: 513342 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5302. Min Act: -0.0001

Data Index: 336511 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6196. Min Act: -0.0001

Data Index: 1635462 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5798. Min Act: -0.0001

Data Index: 289336 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6555. Min Act: -0.0002

Data Index: 869052 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5716. Min Act: -0.0001

Data Index: 1104537 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6121. Min Act: -0.0002

Data Index: 646933 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5687. Min Act: -0.0001

Data Index: 184757 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.6131. Min Act: -0.0002

Data Index: 1200820 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5562. Min Act: -0.0001

Data Index: 1060380 (C4 (Web Text))

Max Activating Token Index: 91