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

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

Neuron 4296 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.4733. Min Act: -0.0000

Data Index: 237317 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1346911 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.2220. Min Act: -0.0000

Data Index: 340847 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1573358 (Python Code)

Max Activating Token Index: 483

Text #4

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.2269. Min Act: -0.0000

Data Index: 1177304 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1351634 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.1380. Min Act: -0.0000

Data Index: 311376 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0919. Min Act: -0.0000

Data Index: 204543 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.1004. Min Act: -0.0000

Data Index: 215700 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1153188 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0862. Min Act: -0.0000

Data Index: 792920 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1097018 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.4733. Min Range: -1.4733

Max Act: 0.9984. Min Act: -0.0000

Data Index: 477159 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0669. Min Act: -0.0000

Data Index: 709421 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0340. Min Act: -0.0000

Data Index: 561287 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0604. Min Act: -0.0000

Data Index: 612776 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.4733. Min Range: -1.4733

Max Act: 0.9579. Min Act: -0.0000

Data Index: 947766 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0175. Min Act: -0.0000

Data Index: 788565 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0474. Min Act: -0.0000

Data Index: 648675 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.4733. Min Range: -1.4733

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1631628 (Python Code)

Max Activating Token Index: 576