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

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

Neuron 1460 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.9553. Min Act: -0.0000

Data Index: 667060 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8440. Min Act: -0.0000

Data Index: 990769 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1525563 (Python Code)

Max Activating Token Index: 183

Text #3

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8081. Min Act: -0.0000

Data Index: 298495 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.8070. Min Act: -0.0000

Data Index: 945996 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1052818 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7455. Min Act: -0.0000

Data Index: 236376 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7849. Min Act: -0.0000

Data Index: 130956 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7570. Min Act: -0.0000

Data Index: 474401 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7482. Min Act: -0.0000

Data Index: 878910 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1631903 (Python Code)

Max Activating Token Index: 439

Text #11

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7201. Min Act: -0.0000

Data Index: 636970 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1591713 (Python Code)

Max Activating Token Index: 224

Text #13

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7638. Min Act: -0.0000

Data Index: 758887 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7205. Min Act: -0.0000

Data Index: 573674 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7416. Min Act: -0.0000

Data Index: 992973 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1403638 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7299. Min Act: -0.0000

Data Index: 226854 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7029. Min Act: -0.0000

Data Index: 285662 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.9553. Min Range: -0.9553

Max Act: 0.7013. Min Act: -0.0000

Data Index: 927768 (C4 (Web Text))

Max Activating Token Index: 555