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

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

Neuron 1443 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3490. Min Range: -2.3490

Max Act: 2.3490. Min Act: -0.0000

Data Index: 982517 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 2.3490. Min Range: -2.3490

Max Act: 2.3013. Min Act: -0.0000

Data Index: 1354990 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 2.3490. Min Range: -2.3490

Max Act: 2.0685. Min Act: -0.0000

Data Index: 798715 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 2.3490. Min Range: -2.3490

Max Act: 2.0572. Min Act: -0.0000

Data Index: 275203 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 2.3490. Min Range: -2.3490

Max Act: 2.1289. Min Act: -0.0000

Data Index: 95701 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 2.3490. Min Range: -2.3490

Max Act: 2.1169. Min Act: -0.0000

Data Index: 1203597 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.9883. Min Act: -0.0000

Data Index: 283038 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.9622. Min Act: -0.0000

Data Index: 1318142 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 2.3490. Min Range: -2.3490

Max Act: 2.0331. Min Act: -0.0000

Data Index: 1586865 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.9499. Min Act: -0.0000

Data Index: 231130 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.9006. Min Act: -0.0000

Data Index: 610764 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.8093. Min Act: -0.0000

Data Index: 195372 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.7263. Min Act: -0.0000

Data Index: 293352 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.8267. Min Act: -0.0000

Data Index: 190056 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.8921. Min Act: -0.0000

Data Index: 1196952 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.7693. Min Act: -0.0000

Data Index: 1246922 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.8730. Min Act: -0.0000

Data Index: 738223 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.6592. Min Act: -0.0000

Data Index: 737363 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.7576. Min Act: -0.0000

Data Index: 1450795 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 2.3490. Min Range: -2.3490

Max Act: 1.7086. Min Act: -0.0000

Data Index: 972052 (C4 (Web Text))

Max Activating Token Index: 83