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

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

Neuron 1825 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0001

Data Index: 126551 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0870. Min Act: -0.0001

Data Index: 644583 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0754. Min Act: -0.0000

Data Index: 238434 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0796. Min Act: -0.0001

Data Index: 22392 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0720. Min Act: -0.0001

Data Index: 19280 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0750. Min Act: -0.0001

Data Index: 168127 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1258711 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1135673 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0725. Min Act: -0.0000

Data Index: 863137 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1433837 (Python Code)

Max Activating Token Index: 580

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0711. Min Act: -0.0000

Data Index: 595152 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0684. Min Act: -0.0001

Data Index: 957509 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0686. Min Act: -0.0001

Data Index: 612105 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1442322 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1524845 (Python Code)

Max Activating Token Index: 1022

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1438373 (Python Code)

Max Activating Token Index: 936

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1057659 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1262403 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0658. Min Act: -0.0001

Data Index: 991599 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0640. Min Act: -0.0000

Data Index: 887920 (C4 (Web Text))

Max Activating Token Index: 322