Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1127 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0997. Min Act: -0.0003

Data Index: 321196 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1636761 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1607626 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0743. Min Act: -0.0002

Data Index: 456409 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0679. Min Act: -0.0003

Data Index: 266143 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1626083 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1623429 (Python Code)

Max Activating Token Index: 409

Text #7

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1404660 (Python Code)

Max Activating Token Index: 963

Text #8

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1522956 (Python Code)

Max Activating Token Index: 143

Text #9

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1538373 (Python Code)

Max Activating Token Index: 421

Text #10

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1468818 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1555975 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0593. Min Act: -0.0002

Data Index: 47022 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0604. Min Act: -0.0002

Data Index: 483347 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0591. Min Act: -0.0003

Data Index: 159845 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1555318 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0572. Min Act: -0.0002

Data Index: 784508 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1603162 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1584008 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1654175 (Python Code)

Max Activating Token Index: 538