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

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

Neuron 5562 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2719. Min Range: -6.2719

Max Act: 6.2719. Min Act: -0.0000

Data Index: 990612 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.9535. Min Act: -0.0000

Data Index: 1048704 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 6.2719. Min Range: -6.2719

Max Act: 6.0984. Min Act: -0.0000

Data Index: 714120 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.9109. Min Act: -0.0000

Data Index: 862715 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.7359. Min Act: -0.0001

Data Index: 701921 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.8331. Min Act: -0.0001

Data Index: 98981 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.7396. Min Act: -0.0000

Data Index: 48995 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.4524. Min Act: -0.0000

Data Index: 78901 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.6235. Min Act: -0.0000

Data Index: 1466526 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.1137. Min Act: -0.0000

Data Index: 1577295 (Python Code)

Max Activating Token Index: 918

Text #10

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.5993. Min Act: -0.0000

Data Index: 130618 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.4171. Min Act: -0.0000

Data Index: 1198253 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.5508. Min Act: -0.0000

Data Index: 1127667 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.7073. Min Act: -0.0000

Data Index: 879182 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.5058. Min Act: -0.0000

Data Index: 832889 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.3703. Min Act: -0.0000

Data Index: 929274 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.3930. Min Act: -0.0001

Data Index: 846323 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.5220. Min Act: -0.0000

Data Index: 283147 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.8527. Min Act: -0.0001

Data Index: 1309492 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 6.2719. Min Range: -6.2719

Max Act: 5.4729. Min Act: -0.0000

Data Index: 350956 (C4 (Web Text))

Max Activating Token Index: 924