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

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

Neuron 5218 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1150329 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0657. Min Act: -0.0002

Data Index: 80611 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0657. Min Act: -0.0002

Data Index: 223513 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1292855 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1034561 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0604. Min Act: -0.0002

Data Index: 949216 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0613. Min Act: -0.0002

Data Index: 740020 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1134182 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1102622 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0585. Min Act: -0.0002

Data Index: 655681 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0580. Min Act: -0.0002

Data Index: 254315 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1012755 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1622098 (Python Code)

Max Activating Token Index: 267

Text #13

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0571. Min Act: -0.0002

Data Index: 594902 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0563. Min Act: -0.0002

Data Index: 476830 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1078889 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0542. Min Act: -0.0002

Data Index: 235604 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0554. Min Act: -0.0002

Data Index: 657331 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1477660 (Python Code)

Max Activating Token Index: 233

Text #19

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0532. Min Act: -0.0002

Data Index: 748567 (C4 (Web Text))

Max Activating Token Index: 245