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

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

Neuron 1090 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6822. Min Act: -0.0001

Data Index: 178068 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6026. Min Act: -0.0001

Data Index: 154009 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5902. Min Act: -0.0001

Data Index: 1200871 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5534. Min Act: -0.0001

Data Index: 441896 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.4797. Min Act: -0.0001

Data Index: 865249 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5199. Min Act: -0.0001

Data Index: 357315 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5635. Min Act: -0.0001

Data Index: 206540 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5444. Min Act: -0.0001

Data Index: 446831 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5522. Min Act: -0.0001

Data Index: 77038 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.4616. Min Act: -0.0001

Data Index: 361591 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.4357. Min Act: -0.0001

Data Index: 481589 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.4933. Min Act: -0.0001

Data Index: 1240417 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5060. Min Act: -0.0001

Data Index: 921222 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1192073 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.4682. Min Act: -0.0001

Data Index: 999412 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.4658. Min Act: -0.0001

Data Index: 444930 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5018. Min Act: -0.0001

Data Index: 404684 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.4686. Min Act: -0.0001

Data Index: 1227650 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.4993. Min Act: -0.0001

Data Index: 535409 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.4977. Min Act: -0.0001

Data Index: 755708 (C4 (Web Text))

Max Activating Token Index: 672